From 0a1ec07a67bd8b0033dace237249654d015efa21 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 20 Apr 2009 01:25:46 +0000 Subject: net: skb_copy_datagram_const_iovec() There's an skb_copy_datagram_iovec() to copy out of a paged skb, but it modifies the iovec, and does not support starting at an offset in the destination. We want both in tun.c, so let's add the function. It's a carbon copy of skb_copy_datagram_iovec() with enough changes to be annoying. Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5fd389162f0..af2b21bdda8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1717,6 +1717,11 @@ extern int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, struct iovec *from, int len); +extern int skb_copy_datagram_const_iovec(const struct sk_buff *from, + int offset, + const struct iovec *to, + int to_offset, + int size); extern void skb_free_datagram(struct sock *sk, struct sk_buff *skb); extern int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); -- cgit v1.2.3-70-g09d2 From 6f26c9a7555e5bcca3560919db9b852015077dae Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 20 Apr 2009 01:26:11 +0000 Subject: tun: fix tun_chr_aio_write so that aio works aio_write gets const struct iovec * but tun_chr_aio_write casts this to struct iovec * and modifies the iovec. As a result, attempts to use io_submit to send packets to a tun device fail with weird errors such as EINVAL. Since tun is the only user of skb_copy_datagram_from_iovec, we can fix this simply by changing the later so that it does not touch the iovec passed to it. Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/tun.c | 13 ++++++++----- include/linux/skbuff.h | 3 ++- include/linux/socket.h | 4 ++-- net/core/datagram.c | 20 ++++++++++++++------ net/core/iovec.c | 7 ++++--- 5 files changed, 30 insertions(+), 17 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3b513e29d39..589f0ca668d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -540,31 +540,34 @@ static inline struct sk_buff *tun_alloc_skb(struct tun_struct *tun, /* Get packet from user space buffer */ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, - struct iovec *iv, size_t count, + const struct iovec *iv, size_t count, int noblock) { struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; struct sk_buff *skb; size_t len = count, align = 0; struct virtio_net_hdr gso = { 0 }; + int offset = 0; if (!(tun->flags & TUN_NO_PI)) { if ((len -= sizeof(pi)) > count) return -EINVAL; - if(memcpy_fromiovec((void *)&pi, iv, sizeof(pi))) + if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi))) return -EFAULT; + offset += sizeof(pi); } if (tun->flags & TUN_VNET_HDR) { if ((len -= sizeof(gso)) > count) return -EINVAL; - if (memcpy_fromiovec((void *)&gso, iv, sizeof(gso))) + if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso))) return -EFAULT; if (gso.hdr_len > len) return -EINVAL; + offset += sizeof(pi); } if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) { @@ -581,7 +584,7 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, return PTR_ERR(skb); } - if (skb_copy_datagram_from_iovec(skb, 0, iv, len)) { + if (skb_copy_datagram_from_iovec(skb, 0, iv, offset, len)) { tun->dev->stats.rx_dropped++; kfree_skb(skb); return -EFAULT; @@ -673,7 +676,7 @@ static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv, DBG(KERN_INFO "%s: tun_chr_write %ld\n", tun->dev->name, count); - result = tun_get_user(tun, (struct iovec *)iv, iov_length(iv, count), + result = tun_get_user(tun, iv, iov_length(iv, count), file->f_flags & O_NONBLOCK); tun_put(tun); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index af2b21bdda8..1b5c3d298f4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1715,7 +1715,8 @@ extern int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, struct iovec *iov); extern int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, - struct iovec *from, + const struct iovec *from, + int from_offset, int len); extern int skb_copy_datagram_const_iovec(const struct sk_buff *from, int offset, diff --git a/include/linux/socket.h b/include/linux/socket.h index 171b08db9c4..42a0396f2c5 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -309,8 +309,8 @@ struct ucred { #ifdef __KERNEL__ extern int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); -extern int memcpy_fromiovecend(unsigned char *kdata, struct iovec *iov, - int offset, int len); +extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, + int offset, int len); extern int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov, int offset, diff --git a/net/core/datagram.c b/net/core/datagram.c index 4dbb05cd572..914d5fa773b 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -435,13 +435,15 @@ EXPORT_SYMBOL(skb_copy_datagram_const_iovec); * @skb: buffer to copy * @offset: offset in the buffer to start copying to * @from: io vector to copy to + * @from_offset: offset in the io vector to start copying from * @len: amount of data to copy to buffer from iovec * * Returns 0 or -EFAULT. - * Note: the iovec is modified during the copy. + * Note: the iovec is not modified during the copy. */ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, - struct iovec *from, int len) + const struct iovec *from, int from_offset, + int len) { int start = skb_headlen(skb); int i, copy = start - offset; @@ -450,11 +452,12 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, if (copy > 0) { if (copy > len) copy = len; - if (memcpy_fromiovec(skb->data + offset, from, copy)) + if (memcpy_fromiovecend(skb->data + offset, from, 0, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; + from_offset += copy; } /* Copy paged appendix. Hmm... why does this look so complicated? */ @@ -473,8 +476,9 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, if (copy > len) copy = len; vaddr = kmap(page); - err = memcpy_fromiovec(vaddr + frag->page_offset + - offset - start, from, copy); + err = memcpy_fromiovecend(vaddr + frag->page_offset + + offset - start, + from, from_offset, copy); kunmap(page); if (err) goto fault; @@ -482,6 +486,7 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, if (!(len -= copy)) return 0; offset += copy; + from_offset += copy; } start = end; } @@ -500,11 +505,14 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, copy = len; if (skb_copy_datagram_from_iovec(list, offset - start, - from, copy)) + from, + from_offset, + copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; + from_offset += copy; } start = end; } diff --git a/net/core/iovec.c b/net/core/iovec.c index a215545c0a3..40a76ce19d9 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -147,10 +147,11 @@ int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len) } /* - * For use with ip_build_xmit + * Copy iovec from kernel. Returns -EFAULT on error. */ -int memcpy_fromiovecend(unsigned char *kdata, struct iovec *iov, int offset, - int len) + +int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, + int offset, int len) { /* Skip over the finished iovecs */ while (offset >= iov->iov_len) { -- cgit v1.2.3-70-g09d2 From 69e3c75f4d541a6eb151b3ef91f34033cb3ad6e1 Mon Sep 17 00:00:00 2001 From: Johann Baudy Date: Mon, 18 May 2009 22:11:22 -0700 Subject: net: TX_RING and packet mmap New packet socket feature that makes packet socket more efficient for transmission. - It reduces number of system call through a PACKET_TX_RING mechanism, based on PACKET_RX_RING (Circular buffer allocated in kernel space which is mmapped from user space). - It minimizes CPU copy using fragmented SKB (almost zero copy). Signed-off-by: Johann Baudy Signed-off-by: David S. Miller --- Documentation/networking/packet_mmap.txt | 140 +++++++- include/linux/if_packet.h | 20 +- include/linux/skbuff.h | 3 + net/packet/af_packet.c | 588 +++++++++++++++++++++++++------ 4 files changed, 616 insertions(+), 135 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index 07c53d59603..a22fd85e379 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -4,16 +4,18 @@ This file documents the CONFIG_PACKET_MMAP option available with the PACKET socket interface on 2.4 and 2.6 kernels. This type of sockets is used for -capture network traffic with utilities like tcpdump or any other that uses -the libpcap library. - -You can find the latest version of this document at +capture network traffic with utilities like tcpdump or any other that needs +raw access to network interface. +You can find the latest version of this document at: http://pusa.uv.es/~ulisses/packet_mmap/ -Please send me your comments to +Howto can be found at: + http://wiki.gnu-log.net (packet_mmap) +Please send your comments to Ulisses Alonso Camaró + Johann Baudy ------------------------------------------------------------------------------- + Why use PACKET_MMAP @@ -25,19 +27,24 @@ to capture each packet, it requires two if you want to get packet's timestamp (like libpcap always does). In the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size -configurable circular buffer mapped in user space. This way reading packets just -needs to wait for them, most of the time there is no need to issue a single -system call. By using a shared buffer between the kernel and the user -also has the benefit of minimizing packet copies. - -It's fine to use PACKET_MMAP to improve the performance of the capture process, -but it isn't everything. At least, if you are capturing at high speeds (this -is relative to the cpu speed), you should check if the device driver of your -network interface card supports some sort of interrupt load mitigation or -(even better) if it supports NAPI, also make sure it is enabled. +configurable circular buffer mapped in user space that can be used to either +send or receive packets. This way reading packets just needs to wait for them, +most of the time there is no need to issue a single system call. Concerning +transmission, multiple packets can be sent through one system call to get the +highest bandwidth. +By using a shared buffer between the kernel and the user also has the benefit +of minimizing packet copies. + +It's fine to use PACKET_MMAP to improve the performance of the capture and +transmission process, but it isn't everything. At least, if you are capturing +at high speeds (this is relative to the cpu speed), you should check if the +device driver of your network interface card supports some sort of interrupt +load mitigation or (even better) if it supports NAPI, also make sure it is +enabled. For transmission, check the MTU (Maximum Transmission Unit) used and +supported by devices of your network. -------------------------------------------------------------------------------- -+ How to use CONFIG_PACKET_MMAP ++ How to use CONFIG_PACKET_MMAP to improve capture process -------------------------------------------------------------------------------- From the user standpoint, you should use the higher level libpcap library, which @@ -57,7 +64,7 @@ the low level details or want to improve libpcap by including PACKET_MMAP support. -------------------------------------------------------------------------------- -+ How to use CONFIG_PACKET_MMAP directly ++ How to use CONFIG_PACKET_MMAP directly to improve capture process -------------------------------------------------------------------------------- From the system calls stand point, the use of PACKET_MMAP involves @@ -66,6 +73,7 @@ the following process: [setup] socket() -------> creation of the capture socket setsockopt() ---> allocation of the circular buffer (ring) + option: PACKET_RX_RING mmap() ---------> mapping of the allocated buffer to the user process @@ -96,6 +104,65 @@ Next I will describe PACKET_MMAP settings and it's constraints, also the mapping of the circular buffer in the user process and the use of this buffer. +-------------------------------------------------------------------------------- ++ How to use CONFIG_PACKET_MMAP directly to improve transmission process +-------------------------------------------------------------------------------- +Transmission process is similar to capture as shown below. + +[setup] socket() -------> creation of the transmission socket + setsockopt() ---> allocation of the circular buffer (ring) + option: PACKET_TX_RING + bind() ---------> bind transmission socket with a network interface + mmap() ---------> mapping of the allocated buffer to the + user process + +[transmission] poll() ---------> wait for free packets (optional) + send() ---------> send all packets that are set as ready in + the ring + The flag MSG_DONTWAIT can be used to return + before end of transfer. + +[shutdown] close() --------> destruction of the transmission socket and + deallocation of all associated resources. + +Binding the socket to your network interface is mandatory (with zero copy) to +know the header size of frames used in the circular buffer. + +As capture, each frame contains two parts: + + -------------------- +| struct tpacket_hdr | Header. It contains the status of +| | of this frame +|--------------------| +| data buffer | +. . Data that will be sent over the network interface. +. . + -------------------- + + bind() associates the socket to your network interface thanks to + sll_ifindex parameter of struct sockaddr_ll. + + Initialization example: + + struct sockaddr_ll my_addr; + struct ifreq s_ifr; + ... + + strncpy (s_ifr.ifr_name, "eth0", sizeof(s_ifr.ifr_name)); + + /* get interface index of eth0 */ + ioctl(this->socket, SIOCGIFINDEX, &s_ifr); + + /* fill sockaddr_ll struct to prepare binding */ + my_addr.sll_family = AF_PACKET; + my_addr.sll_protocol = ETH_P_ALL; + my_addr.sll_ifindex = s_ifr.ifr_ifindex; + + /* bind socket to eth0 */ + bind(this->socket, (struct sockaddr *)&my_addr, sizeof(struct sockaddr_ll)); + + A complete tutorial is available at: http://wiki.gnu-log.net/ + -------------------------------------------------------------------------------- + PACKET_MMAP settings -------------------------------------------------------------------------------- @@ -103,7 +170,10 @@ the use of this buffer. To setup PACKET_MMAP from user level code is done with a call like + - Capture process setsockopt(fd, SOL_PACKET, PACKET_RX_RING, (void *) &req, sizeof(req)) + - Transmission process + setsockopt(fd, SOL_PACKET, PACKET_TX_RING, (void *) &req, sizeof(req)) The most significant argument in the previous call is the req parameter, this parameter must to have the following structure: @@ -117,11 +187,11 @@ this parameter must to have the following structure: }; This structure is defined in /usr/include/linux/if_packet.h and establishes a -circular buffer (ring) of unswappable memory mapped in the capture process. +circular buffer (ring) of unswappable memory. Being mapped in the capture process allows reading the captured frames and related meta-information like timestamps without requiring a system call. -Captured frames are grouped in blocks. Each block is a physically contiguous +Frames are grouped in blocks. Each block is a physically contiguous region of memory and holds tp_block_size/tp_frame_size frames. The total number of blocks is tp_block_nr. Note that tp_frame_nr is a redundant parameter because @@ -336,6 +406,7 @@ struct tpacket_hdr). If this field is 0 means that the frame is ready to be used for the kernel, If not, there is a frame the user can read and the following flags apply: ++++ Capture process: from include/linux/if_packet.h #define TP_STATUS_COPY 2 @@ -391,6 +462,37 @@ packets are in the ring: It doesn't incur in a race condition to first check the status value and then poll for frames. + +++ Transmission process +Those defines are also used for transmission: + + #define TP_STATUS_AVAILABLE 0 // Frame is available + #define TP_STATUS_SEND_REQUEST 1 // Frame will be sent on next send() + #define TP_STATUS_SENDING 2 // Frame is currently in transmission + #define TP_STATUS_WRONG_FORMAT 4 // Frame format is not correct + +First, the kernel initializes all frames to TP_STATUS_AVAILABLE. To send a +packet, the user fills a data buffer of an available frame, sets tp_len to +current data buffer size and sets its status field to TP_STATUS_SEND_REQUEST. +This can be done on multiple frames. Once the user is ready to transmit, it +calls send(). Then all buffers with status equal to TP_STATUS_SEND_REQUEST are +forwarded to the network device. The kernel updates each status of sent +frames with TP_STATUS_SENDING until the end of transfer. +At the end of each transfer, buffer status returns to TP_STATUS_AVAILABLE. + + header->tp_len = in_i_size; + header->tp_status = TP_STATUS_SEND_REQUEST; + retval = send(this->socket, NULL, 0, 0); + +The user can also use poll() to check if a buffer is available: +(status == TP_STATUS_SENDING) + + struct pollfd pfd; + pfd.fd = fd; + pfd.revents = 0; + pfd.events = POLLOUT; + retval = poll(&pfd, 1, timeout); + -------------------------------------------------------------------------------- + THANKS -------------------------------------------------------------------------------- diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 18db0668065..5b2badeb949 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -46,6 +46,8 @@ struct sockaddr_ll #define PACKET_VERSION 10 #define PACKET_HDRLEN 11 #define PACKET_RESERVE 12 +#define PACKET_TX_RING 13 +#define PACKET_LOSS 14 struct tpacket_stats { @@ -63,14 +65,22 @@ struct tpacket_auxdata __u16 tp_vlan_tci; }; +/* Rx ring - header status */ +#define TP_STATUS_KERNEL 0x0 +#define TP_STATUS_USER 0x1 +#define TP_STATUS_COPY 0x2 +#define TP_STATUS_LOSING 0x4 +#define TP_STATUS_CSUMNOTREADY 0x8 + +/* Tx ring - header status */ +#define TP_STATUS_AVAILABLE 0x0 +#define TP_STATUS_SEND_REQUEST 0x1 +#define TP_STATUS_SENDING 0x2 +#define TP_STATUS_WRONG_FORMAT 0x4 + struct tpacket_hdr { unsigned long tp_status; -#define TP_STATUS_KERNEL 0 -#define TP_STATUS_USER 1 -#define TP_STATUS_COPY 2 -#define TP_STATUS_LOSING 4 -#define TP_STATUS_CSUMNOTREADY 8 unsigned int tp_len; unsigned int tp_snaplen; unsigned short tp_mac; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1b5c3d298f4..aff494ba6a3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -203,6 +203,9 @@ struct skb_shared_info { #ifdef CONFIG_HAS_DMA dma_addr_t dma_maps[MAX_SKB_FRAGS + 1]; #endif + /* Intermediate layers must ensure that destructor_arg + * remains valid until skb destructor */ + void * destructor_arg; }; /* We divide dataref into two halves. The higher 16 bits hold references diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f546e81acc4..766e6b41f7c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -39,6 +39,7 @@ * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. + * Johann Baudy : Added TX RING. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -157,7 +158,25 @@ struct packet_mreq_max }; #ifdef CONFIG_PACKET_MMAP -static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing); +static int packet_set_ring(struct sock *sk, struct tpacket_req *req, + int closing, int tx_ring); + +struct packet_ring_buffer { + char * *pg_vec; + unsigned int head; + unsigned int frames_per_block; + unsigned int frame_size; + unsigned int frame_max; + + unsigned int pg_vec_order; + unsigned int pg_vec_pages; + unsigned int pg_vec_len; + + atomic_t pending; +}; + +struct packet_sock; +static int tpacket_snd(struct packet_sock *po, struct msghdr *msg); #endif static void packet_flush_mclist(struct sock *sk); @@ -167,11 +186,8 @@ struct packet_sock { struct sock sk; struct tpacket_stats stats; #ifdef CONFIG_PACKET_MMAP - char * *pg_vec; - unsigned int head; - unsigned int frames_per_block; - unsigned int frame_size; - unsigned int frame_max; + struct packet_ring_buffer rx_ring; + struct packet_ring_buffer tx_ring; int copy_thresh; #endif struct packet_type prot_hook; @@ -185,12 +201,10 @@ struct packet_sock { struct packet_mclist *mclist; #ifdef CONFIG_PACKET_MMAP atomic_t mapped; - unsigned int pg_vec_order; - unsigned int pg_vec_pages; - unsigned int pg_vec_len; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; + unsigned int tp_loss:1; #endif }; @@ -206,36 +220,33 @@ struct packet_skb_cb { #ifdef CONFIG_PACKET_MMAP -static void *packet_lookup_frame(struct packet_sock *po, unsigned int position, - int status) +static void __packet_set_status(struct packet_sock *po, void *frame, int status) { - unsigned int pg_vec_pos, frame_offset; union { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; void *raw; } h; - pg_vec_pos = position / po->frames_per_block; - frame_offset = position % po->frames_per_block; - - h.raw = po->pg_vec[pg_vec_pos] + (frame_offset * po->frame_size); + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - if (status != (h.h1->tp_status ? TP_STATUS_USER : - TP_STATUS_KERNEL)) - return NULL; + h.h1->tp_status = status; + flush_dcache_page(virt_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - if (status != (h.h2->tp_status ? TP_STATUS_USER : - TP_STATUS_KERNEL)) - return NULL; + h.h2->tp_status = status; + flush_dcache_page(virt_to_page(&h.h2->tp_status)); break; + default: + printk(KERN_ERR "TPACKET version not supported\n"); + BUG(); } - return h.raw; + + smp_wmb(); } -static void __packet_set_status(struct packet_sock *po, void *frame, int status) +static int __packet_get_status(struct packet_sock *po, void *frame) { union { struct tpacket_hdr *h1; @@ -243,16 +254,66 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) void *raw; } h; + smp_rmb(); + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; - break; + flush_dcache_page(virt_to_page(&h.h1->tp_status)); + return h.h1->tp_status; case TPACKET_V2: - h.h2->tp_status = status; - break; + flush_dcache_page(virt_to_page(&h.h2->tp_status)); + return h.h2->tp_status; + default: + printk(KERN_ERR "TPACKET version not supported\n"); + BUG(); + return 0; } } + +static void *packet_lookup_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + unsigned int position, + int status) +{ + unsigned int pg_vec_pos, frame_offset; + union { + struct tpacket_hdr *h1; + struct tpacket2_hdr *h2; + void *raw; + } h; + + pg_vec_pos = position / rb->frames_per_block; + frame_offset = position % rb->frames_per_block; + + h.raw = rb->pg_vec[pg_vec_pos] + (frame_offset * rb->frame_size); + + if (status != __packet_get_status(po, h.raw)) + return NULL; + + return h.raw; +} + +static inline void *packet_current_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + int status) +{ + return packet_lookup_frame(po, rb, rb->head, status); +} + +static inline void *packet_previous_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + int status) +{ + unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; + return packet_lookup_frame(po, rb, previous, status); +} + +static inline void packet_increment_head(struct packet_ring_buffer *buff) +{ + buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; +} + #endif static inline struct packet_sock *pkt_sk(struct sock *sk) @@ -648,7 +709,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe macoff = netoff - maclen; } - if (macoff + snaplen > po->frame_size) { + if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && atomic_read(&sk->sk_rmem_alloc) + skb->truesize < (unsigned)sk->sk_rcvbuf) { @@ -661,16 +722,16 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe if (copy_skb) skb_set_owner_r(copy_skb, sk); } - snaplen = po->frame_size - macoff; + snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) snaplen = 0; } spin_lock(&sk->sk_receive_queue.lock); - h.raw = packet_lookup_frame(po, po->head, TP_STATUS_KERNEL); + h.raw = packet_current_frame(po, &po->rx_ring, TP_STATUS_KERNEL); if (!h.raw) goto ring_is_full; - po->head = po->head != po->frame_max ? po->head+1 : 0; + packet_increment_head(&po->rx_ring); po->stats.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; @@ -727,7 +788,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe __packet_set_status(po, h.raw, status); smp_mb(); - { struct page *p_start, *p_end; u8 *h_end = h.raw + macoff + snaplen - 1; @@ -760,10 +820,249 @@ ring_is_full: goto drop_n_restore; } -#endif +static void tpacket_destruct_skb(struct sk_buff *skb) +{ + struct packet_sock *po = pkt_sk(skb->sk); + void * ph; + BUG_ON(skb == NULL); -static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, + if (likely(po->tx_ring.pg_vec)) { + ph = skb_shinfo(skb)->destructor_arg; + BUG_ON(__packet_get_status(po, ph) != TP_STATUS_SENDING); + BUG_ON(atomic_read(&po->tx_ring.pending) == 0); + atomic_dec(&po->tx_ring.pending); + __packet_set_status(po, ph, TP_STATUS_AVAILABLE); + } + + sock_wfree(skb); +} + +static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff * skb, + void * frame, struct net_device *dev, int size_max, + __be16 proto, unsigned char * addr) +{ + union { + struct tpacket_hdr *h1; + struct tpacket2_hdr *h2; + void *raw; + } ph; + int to_write, offset, len, tp_len, nr_frags, len_max; + struct socket *sock = po->sk.sk_socket; + struct page *page; + void *data; + int err; + + ph.raw = frame; + + skb->protocol = proto; + skb->dev = dev; + skb->priority = po->sk.sk_priority; + skb_shinfo(skb)->destructor_arg = ph.raw; + + switch (po->tp_version) { + case TPACKET_V2: + tp_len = ph.h2->tp_len; + break; + default: + tp_len = ph.h1->tp_len; + break; + } + if (unlikely(tp_len > size_max)) { + printk(KERN_ERR "packet size is too long (%d > %d)\n", + tp_len, size_max); + return -EMSGSIZE; + } + + skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reset_network_header(skb); + + data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll); + to_write = tp_len; + + if (sock->type == SOCK_DGRAM) { + err = dev_hard_header(skb, dev, ntohs(proto), addr, + NULL, tp_len); + if (unlikely(err < 0)) + return -EINVAL; + } else if (dev->hard_header_len ) { + /* net device doesn't like empty head */ + if (unlikely(tp_len <= dev->hard_header_len)) { + printk(KERN_ERR "packet size is too short " + "(%d < %d)\n", tp_len, + dev->hard_header_len); + return -EINVAL; + } + + skb_push(skb, dev->hard_header_len); + err = skb_store_bits(skb, 0, data, + dev->hard_header_len); + if (unlikely(err)) + return err; + + data += dev->hard_header_len; + to_write -= dev->hard_header_len; + } + + err = -EFAULT; + page = virt_to_page(data); + offset = offset_in_page(data); + len_max = PAGE_SIZE - offset; + len = ((to_write > len_max) ? len_max : to_write); + + skb->data_len = to_write; + skb->len += to_write; + skb->truesize += to_write; + atomic_add(to_write, &po->sk.sk_wmem_alloc); + + while (likely(to_write)) { + nr_frags = skb_shinfo(skb)->nr_frags; + + if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { + printk(KERN_ERR "Packet exceed the number " + "of skb frags(%lu)\n", + MAX_SKB_FRAGS); + return -EFAULT; + } + + flush_dcache_page(page); + get_page(page); + skb_fill_page_desc(skb, + nr_frags, + page++, offset, len); + to_write -= len; + offset = 0; + len_max = PAGE_SIZE; + len = ((to_write > len_max) ? len_max : to_write); + } + + return tp_len; +} + +static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) +{ + struct socket *sock; + struct sk_buff *skb; + struct net_device *dev; + __be16 proto; + int ifindex, err, reserve = 0; + void * ph; + struct sockaddr_ll *saddr=(struct sockaddr_ll *)msg->msg_name; + int tp_len, size_max; + unsigned char *addr; + int len_sum = 0; + int status = 0; + + sock = po->sk.sk_socket; + + mutex_lock(&po->pg_vec_lock); + + err = -EBUSY; + if (saddr == NULL) { + ifindex = po->ifindex; + proto = po->num; + addr = NULL; + } else { + err = -EINVAL; + if (msg->msg_namelen < sizeof(struct sockaddr_ll)) + goto out; + if (msg->msg_namelen < (saddr->sll_halen + + offsetof(struct sockaddr_ll, + sll_addr))) + goto out; + ifindex = saddr->sll_ifindex; + proto = saddr->sll_protocol; + addr = saddr->sll_addr; + } + + dev = dev_get_by_index(sock_net(&po->sk), ifindex); + err = -ENXIO; + if (unlikely(dev == NULL)) + goto out; + + reserve = dev->hard_header_len; + + err = -ENETDOWN; + if (unlikely(!(dev->flags & IFF_UP))) + goto out_put; + + size_max = po->tx_ring.frame_size + - sizeof(struct skb_shared_info) + - po->tp_hdrlen + - LL_ALLOCATED_SPACE(dev) + - sizeof(struct sockaddr_ll); + + if (size_max > dev->mtu + reserve) + size_max = dev->mtu + reserve; + + do { + ph = packet_current_frame(po, &po->tx_ring, + TP_STATUS_SEND_REQUEST); + + if (unlikely(ph == NULL)) { + schedule(); + continue; + } + + status = TP_STATUS_SEND_REQUEST; + skb = sock_alloc_send_skb(&po->sk, + LL_ALLOCATED_SPACE(dev) + + sizeof(struct sockaddr_ll), + 0, &err); + + if (unlikely(skb == NULL)) + goto out_status; + + tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, + addr); + + if (unlikely(tp_len < 0)) { + if (po->tp_loss) { + __packet_set_status(po, ph, + TP_STATUS_AVAILABLE); + packet_increment_head(&po->tx_ring); + kfree_skb(skb); + continue; + } else { + status = TP_STATUS_WRONG_FORMAT; + err = tp_len; + goto out_status; + } + } + + skb->destructor = tpacket_destruct_skb; + __packet_set_status(po, ph, TP_STATUS_SENDING); + atomic_inc(&po->tx_ring.pending); + + status = TP_STATUS_SEND_REQUEST; + err = dev_queue_xmit(skb); + if (unlikely(err > 0 && (err = net_xmit_errno(err)) != 0)) + goto out_xmit; + packet_increment_head(&po->tx_ring); + len_sum += tp_len; + } + while (likely((ph != NULL) || ((!(msg->msg_flags & MSG_DONTWAIT)) + && (atomic_read(&po->tx_ring.pending)))) + ); + + err = len_sum; + goto out_put; + +out_xmit: + skb->destructor = sock_wfree; + atomic_dec(&po->tx_ring.pending); +out_status: + __packet_set_status(po, ph, status); + kfree_skb(skb); +out_put: + dev_put(dev); +out: + mutex_unlock(&po->pg_vec_lock); + return err; +} +#endif + +static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; @@ -854,6 +1153,19 @@ out: return err; } +static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t len) +{ +#ifdef CONFIG_PACKET_MMAP + struct sock *sk = sock->sk; + struct packet_sock *po = pkt_sk(sk); + if (po->tx_ring.pg_vec) + return tpacket_snd(po, msg); + else +#endif + return packet_snd(sock, msg, len); +} + /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. @@ -864,6 +1176,9 @@ static int packet_release(struct socket *sock) struct sock *sk = sock->sk; struct packet_sock *po; struct net *net; +#ifdef CONFIG_PACKET_MMAP + struct tpacket_req req; +#endif if (!sk) return 0; @@ -893,11 +1208,13 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); #ifdef CONFIG_PACKET_MMAP - if (po->pg_vec) { - struct tpacket_req req; - memset(&req, 0, sizeof(req)); - packet_set_ring(sk, &req, 1); - } + memset(&req, 0, sizeof(req)); + + if (po->rx_ring.pg_vec) + packet_set_ring(sk, &req, 1, 0); + + if (po->tx_ring.pg_vec) + packet_set_ring(sk, &req, 1, 1); #endif /* @@ -1391,7 +1708,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (level != SOL_PACKET) return -ENOPROTOOPT; - switch(optname) { + switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { @@ -1415,6 +1732,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv #ifdef CONFIG_PACKET_MMAP case PACKET_RX_RING: + case PACKET_TX_RING: { struct tpacket_req req; @@ -1422,7 +1740,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return -EINVAL; if (copy_from_user(&req,optval,sizeof(req))) return -EFAULT; - return packet_set_ring(sk, &req, 0); + return packet_set_ring(sk, &req, 0, optname == PACKET_TX_RING); } case PACKET_COPY_THRESH: { @@ -1442,7 +1760,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->pg_vec) + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; @@ -1461,13 +1779,26 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->pg_vec) + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; po->tp_reserve = val; return 0; } + case PACKET_LOSS: + { + unsigned int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) + return -EBUSY; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + po->tp_loss = !!val; + return 0; + } #endif case PACKET_AUXDATA: { @@ -1517,7 +1848,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, if (len < 0) return -EINVAL; - switch(optname) { + switch (optname) { case PACKET_STATISTICS: if (len > sizeof(struct tpacket_stats)) len = sizeof(struct tpacket_stats); @@ -1573,6 +1904,12 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, val = po->tp_reserve; data = &val; break; + case PACKET_LOSS: + if (len > sizeof(unsigned int)) + len = sizeof(unsigned int); + val = po->tp_loss; + data = &val; + break; #endif default: return -ENOPROTOOPT; @@ -1643,7 +1980,7 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd, { struct sock *sk = sock->sk; - switch(cmd) { + switch (cmd) { case SIOCOUTQ: { int amount = atomic_read(&sk->sk_wmem_alloc); @@ -1705,13 +2042,17 @@ static unsigned int packet_poll(struct file * file, struct socket *sock, unsigned int mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); - if (po->pg_vec) { - unsigned last = po->head ? po->head-1 : po->frame_max; - - if (packet_lookup_frame(po, last, TP_STATUS_USER)) + if (po->rx_ring.pg_vec) { + if (!packet_previous_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= POLLIN | POLLRDNORM; } spin_unlock_bh(&sk->sk_receive_queue.lock); + spin_lock_bh(&sk->sk_write_queue.lock); + if (po->tx_ring.pg_vec) { + if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) + mask |= POLLOUT | POLLWRNORM; + } + spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } @@ -1788,21 +2129,33 @@ out_free_pgvec: goto out; } -static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing) +static int packet_set_ring(struct sock *sk, struct tpacket_req *req, + int closing, int tx_ring) { char **pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); int was_running, order = 0; + struct packet_ring_buffer *rb; + struct sk_buff_head *rb_queue; __be16 num; - int err = 0; + int err; - if (req->tp_block_nr) { - int i; + rb = tx_ring ? &po->tx_ring : &po->rx_ring; + rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; - /* Sanity tests and some calculations */ + err = -EBUSY; + if (!closing) { + if (atomic_read(&po->mapped)) + goto out; + if (atomic_read(&rb->pending)) + goto out; + } - if (unlikely(po->pg_vec)) - return -EBUSY; + if (req->tp_block_nr) { + /* Sanity tests and some calculations */ + err = -EBUSY; + if (unlikely(rb->pg_vec)) + goto out; switch (po->tp_version) { case TPACKET_V1: @@ -1813,42 +2166,35 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing break; } + err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) - return -EINVAL; + goto out; if (unlikely(req->tp_block_size & (PAGE_SIZE - 1))) - return -EINVAL; + goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + - po->tp_reserve)) - return -EINVAL; + po->tp_reserve)) + goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) - return -EINVAL; + goto out; - po->frames_per_block = req->tp_block_size/req->tp_frame_size; - if (unlikely(po->frames_per_block <= 0)) - return -EINVAL; - if (unlikely((po->frames_per_block * req->tp_block_nr) != - req->tp_frame_nr)) - return -EINVAL; + rb->frames_per_block = req->tp_block_size/req->tp_frame_size; + if (unlikely(rb->frames_per_block <= 0)) + goto out; + if (unlikely((rb->frames_per_block * req->tp_block_nr) != + req->tp_frame_nr)) + goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; - - for (i = 0; i < req->tp_block_nr; i++) { - void *ptr = pg_vec[i]; - int k; - - for (k = 0; k < po->frames_per_block; k++) { - __packet_set_status(po, ptr, TP_STATUS_KERNEL); - ptr += req->tp_frame_size; - } - } - /* Done */ - } else { + } + /* Done */ + else { + err = -EINVAL; if (unlikely(req->tp_frame_nr)) - return -EINVAL; + goto out; } lock_sock(sk); @@ -1872,23 +2218,24 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing if (closing || atomic_read(&po->mapped) == 0) { err = 0; #define XC(a, b) ({ __typeof__ ((a)) __t; __t = (a); (a) = (b); __t; }) - - spin_lock_bh(&sk->sk_receive_queue.lock); - pg_vec = XC(po->pg_vec, pg_vec); - po->frame_max = (req->tp_frame_nr - 1); - po->head = 0; - po->frame_size = req->tp_frame_size; - spin_unlock_bh(&sk->sk_receive_queue.lock); - - order = XC(po->pg_vec_order, order); - req->tp_block_nr = XC(po->pg_vec_len, req->tp_block_nr); - - po->pg_vec_pages = req->tp_block_size/PAGE_SIZE; - po->prot_hook.func = po->pg_vec ? tpacket_rcv : packet_rcv; - skb_queue_purge(&sk->sk_receive_queue); + spin_lock_bh(&rb_queue->lock); + pg_vec = XC(rb->pg_vec, pg_vec); + rb->frame_max = (req->tp_frame_nr - 1); + rb->head = 0; + rb->frame_size = req->tp_frame_size; + spin_unlock_bh(&rb_queue->lock); + + order = XC(rb->pg_vec_order, order); + req->tp_block_nr = XC(rb->pg_vec_len, req->tp_block_nr); + + rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; + po->prot_hook.func = (po->rx_ring.pg_vec) ? + tpacket_rcv : packet_rcv; + skb_queue_purge(rb_queue); #undef XC if (atomic_read(&po->mapped)) - printk(KERN_DEBUG "packet_mmap: vma is busy: %d\n", atomic_read(&po->mapped)); + printk(KERN_DEBUG "packet_mmap: vma is busy: %d\n", + atomic_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); @@ -1909,11 +2256,13 @@ out: return err; } -static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) +static int packet_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - unsigned long size; + unsigned long size, expected_size; + struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; @@ -1921,26 +2270,43 @@ static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_st if (vma->vm_pgoff) return -EINVAL; - size = vma->vm_end - vma->vm_start; - mutex_lock(&po->pg_vec_lock); - if (po->pg_vec == NULL) + + expected_size = 0; + for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { + if (rb->pg_vec) { + expected_size += rb->pg_vec_len + * rb->pg_vec_pages + * PAGE_SIZE; + } + } + + if (expected_size == 0) goto out; - if (size != po->pg_vec_len*po->pg_vec_pages*PAGE_SIZE) + + size = vma->vm_end - vma->vm_start; + if (size != expected_size) goto out; start = vma->vm_start; - for (i = 0; i < po->pg_vec_len; i++) { - struct page *page = virt_to_page(po->pg_vec[i]); - int pg_num; - - for (pg_num = 0; pg_num < po->pg_vec_pages; pg_num++, page++) { - err = vm_insert_page(vma, start, page); - if (unlikely(err)) - goto out; - start += PAGE_SIZE; + for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { + if (rb->pg_vec == NULL) + continue; + + for (i = 0; i < rb->pg_vec_len; i++) { + struct page *page = virt_to_page(rb->pg_vec[i]); + int pg_num; + + for (pg_num = 0; pg_num < rb->pg_vec_pages; + pg_num++,page++) { + err = vm_insert_page(vma, start, page); + if (unlikely(err)) + goto out; + start += PAGE_SIZE; + } } } + atomic_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; -- cgit v1.2.3-70-g09d2 From dfbf97f3ac980b69dfbc41c83a208211a38443e8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 2 Jun 2009 05:13:45 +0000 Subject: net: add _skb_dst opaque field struct sk_buff uses one union to define dst and rtable fields. We want to replace direct access to these pointers by accessors. First patch adds a new "unsigned long _skb_dst;" opaque field in this union. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index aff494ba6a3..d4d7c666ca6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -325,6 +325,7 @@ struct sk_buff { union { struct dst_entry *dst; struct rtable *rtable; + unsigned long _skb_dst; }; #ifdef CONFIG_XFRM struct sec_path *sp; -- cgit v1.2.3-70-g09d2 From 511c3f92ad5b6d9f8f6464be1b4f85f0422be91a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 2 Jun 2009 05:14:27 +0000 Subject: net: skb->rtable accessor Define skb_rtable(const struct sk_buff *skb) accessor to get rtable from skb Delete skb->rtable field Setting rtable is not allowed, just set dst instead as rtable is an alias. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/appletalk/ipddp.c | 2 +- include/linux/skbuff.h | 6 +++++- include/net/route.h | 2 +- net/bridge/br_netfilter.c | 25 +++++++++++++--------- net/dccp/ipv4.c | 6 +++--- net/ipv4/arp.c | 4 ++-- net/ipv4/icmp.c | 10 ++++----- net/ipv4/igmp.c | 2 +- net/ipv4/ip_forward.c | 2 +- net/ipv4/ip_gre.c | 4 ++-- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_options.c | 16 +++++++------- net/ipv4/ip_output.c | 10 ++++----- net/ipv4/ip_sockglue.c | 2 +- net/ipv4/ipip.c | 2 +- net/ipv4/ipmr.c | 6 +++--- net/ipv4/netfilter/ipt_MASQUERADE.c | 2 +- net/ipv4/netfilter/nf_nat_helper.c | 4 ++-- net/ipv4/route.c | 37 ++++++++++++++++++++------------- net/ipv4/tcp_ipv4.c | 4 ++-- net/netfilter/nf_conntrack_netbios_ns.c | 2 +- net/sched/em_meta.c | 4 ++-- net/sctp/protocol.c | 8 +++---- 23 files changed, 89 insertions(+), 73 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c index 9832b757f10..78cea5e80b1 100644 --- a/drivers/net/appletalk/ipddp.c +++ b/drivers/net/appletalk/ipddp.c @@ -115,7 +115,7 @@ static struct net_device * __init ipddp_init(void) */ static int ipddp_xmit(struct sk_buff *skb, struct net_device *dev) { - __be32 paddr = ((struct rtable*)skb->dst)->rt_gateway; + __be32 paddr = skb_rtable(skb)->rt_gateway; struct ddpehdr *ddp; struct ipddp_route *rt; struct atalk_addr *our_addr; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d4d7c666ca6..a3ae3c52583 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -324,7 +324,6 @@ struct sk_buff { union { struct dst_entry *dst; - struct rtable *rtable; unsigned long _skb_dst; }; #ifdef CONFIG_XFRM @@ -427,6 +426,11 @@ extern void skb_dma_unmap(struct device *dev, struct sk_buff *skb, enum dma_data_direction dir); #endif +static inline struct rtable *skb_rtable(const struct sk_buff *skb) +{ + return (struct rtable *)skb->_skb_dst; +} + extern void kfree_skb(struct sk_buff *skb); extern void consume_skb(struct sk_buff *skb); extern void __kfree_skb(struct sk_buff *skb); diff --git a/include/net/route.h b/include/net/route.h index 4e8cae0e584..40f6346ef49 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -210,7 +210,7 @@ static inline struct inet_peer *rt_get_peer(struct rtable *rt) static inline int inet_iif(const struct sk_buff *skb) { - return skb->rtable->rt_iif; + return skb_rtable(skb)->rt_iif; } #endif /* _ROUTE_H */ diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index e4a418fcb35..e0ceb66a9ec 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -228,6 +228,7 @@ int nf_bridge_copy_header(struct sk_buff *skb) static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct rtable *rt; if (nf_bridge->mask & BRNF_PKT_TYPE) { skb->pkt_type = PACKET_OTHERHOST; @@ -235,12 +236,13 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - skb->rtable = bridge_parent_rtable(nf_bridge->physindev); - if (!skb->rtable) { + rt = bridge_parent_rtable(nf_bridge->physindev); + if (!rt) { kfree_skb(skb); return 0; } - dst_hold(&skb->rtable->u.dst); + dst_hold(&rt->u.dst); + skb->dst = &rt->u.dst; skb->dev = nf_bridge->physindev; nf_bridge_push_encap_header(skb); @@ -338,6 +340,7 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) struct net_device *dev = skb->dev; struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct rtable *rt; int err; if (nf_bridge->mask & BRNF_PKT_TYPE) { @@ -347,7 +350,6 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; if (dnat_took_place(skb)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { - struct rtable *rt; struct flowi fl = { .nl_u = { .ip4_u = { @@ -404,12 +406,13 @@ bridged_dnat: skb->pkt_type = PACKET_HOST; } } else { - skb->rtable = bridge_parent_rtable(nf_bridge->physindev); - if (!skb->rtable) { + rt = bridge_parent_rtable(nf_bridge->physindev); + if (!rt) { kfree_skb(skb); return 0; } - dst_hold(&skb->rtable->u.dst); + dst_hold(&rt->u.dst); + skb->dst = &rt->u.dst; } skb->dev = nf_bridge->physindev; @@ -628,9 +631,11 @@ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (skb->rtable && skb->rtable == bridge_parent_rtable(in)) { - dst_release(&skb->rtable->u.dst); - skb->rtable = NULL; + struct rtable *rt = skb_rtable(skb); + + if (rt && rt == bridge_parent_rtable(in)) { + dst_release(&rt->u.dst); + skb->dst = NULL; } return NF_ACCEPT; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index d1dd95289b8..2cf48ba0dbb 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -452,7 +452,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt; - struct flowi fl = { .oif = skb->rtable->rt_iif, + struct flowi fl = { .oif = skb_rtable(skb)->rt_iif, .nl_u = { .ip4_u = { .daddr = ip_hdr(skb)->saddr, .saddr = ip_hdr(skb)->daddr, @@ -514,7 +514,7 @@ static void dccp_v4_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; - if (rxskb->rtable->rt_type != RTN_LOCAL) + if (skb_rtable(rxskb)->rt_type != RTN_LOCAL) return; dst = dccp_v4_route_skb(net, ctl_sk, rxskb); @@ -567,7 +567,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); /* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */ - if (skb->rtable->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return 0; /* discard, don't send a reset here */ if (dccp_bad_service_code(sk, service)) { diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f11931c1838..816494f271a 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -474,7 +474,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb) return 1; } - paddr = skb->rtable->rt_gateway; + paddr = skb_rtable(skb)->rt_gateway; if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr, paddr, dev)) return 0; @@ -817,7 +817,7 @@ static int arp_process(struct sk_buff *skb) if (arp->ar_op == htons(ARPOP_REQUEST) && ip_route_input(skb, tip, sip, 0, dev) == 0) { - rt = skb->rtable; + rt = skb_rtable(skb); addr_type = rt->rt_type; if (addr_type == RTN_LOCAL) { diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 3f50807237e..94f75efae93 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -356,7 +356,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { struct ipcm_cookie ipc; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->u.dst.dev); struct sock *sk; struct inet_sock *inet; @@ -416,7 +416,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) struct iphdr *iph; int room; struct icmp_bxm icmp_param; - struct rtable *rt = skb_in->rtable; + struct rtable *rt = skb_rtable(skb_in); struct ipcm_cookie ipc; __be32 saddr; u8 tos; @@ -596,7 +596,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) RT_TOS(tos), rt2->u.dst.dev); dst_release(&rt2->u.dst); - rt2 = skb_in->rtable; + rt2 = skb_rtable(skb_in); skb_in->dst = odst; } @@ -926,7 +926,7 @@ static void icmp_address(struct sk_buff *skb) static void icmp_address_reply(struct sk_buff *skb) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct net_device *dev = skb->dev; struct in_device *in_dev; struct in_ifaddr *ifa; @@ -970,7 +970,7 @@ static void icmp_discard(struct sk_buff *skb) int icmp_rcv(struct sk_buff *skb) { struct icmphdr *icmph; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->u.dst.dev); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index e6058a50379..afabd2758b6 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -948,7 +948,7 @@ int igmp_rcv(struct sk_buff *skb) case IGMPV2_HOST_MEMBERSHIP_REPORT: case IGMPV3_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ - if (skb->rtable->fl.iif == 0) + if (skb_rtable(skb)->fl.iif == 0) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index df3fe50bbf0..0761cd9bbd1 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -81,7 +81,7 @@ int ip_forward(struct sk_buff *skb) if (!xfrm4_route_forward(skb)) goto drop; - rt = skb->rtable; + rt = skb_rtable(skb); if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway) goto sr_failed; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 77436e2732e..85ddad45a91 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -602,7 +602,7 @@ static int ipgre_rcv(struct sk_buff *skb) #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { /* Looped back packet, drop it! */ - if (skb->rtable->fl.iif == 0) + if (skb_rtable(skb)->fl.iif == 0) goto drop; stats->multicast++; skb->pkt_type = PACKET_BROADCAST; @@ -704,7 +704,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } if (skb->protocol == htons(ETH_P_IP)) { - rt = skb->rtable; + rt = skb_rtable(skb); if ((dst = rt->rt_gateway) == 0) goto tx_error_icmp; } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 40f6206b2aa..cea784b0aa4 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -357,7 +357,7 @@ static int ip_rcv_finish(struct sk_buff *skb) if (iph->ihl > 5 && ip_rcv_options(skb)) goto drop; - rt = skb->rtable; + rt = skb_rtable(skb); if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INMCAST, skb->len); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 2c88da6e786..7e1074ffdbd 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -102,7 +102,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) sptr = skb_network_header(skb); dptr = dopt->__data; - daddr = skb->rtable->rt_spec_dst; + daddr = skb_rtable(skb)->rt_spec_dst; if (sopt->rr) { optlen = sptr[sopt->rr+1]; @@ -257,7 +257,7 @@ int ip_options_compile(struct net *net, struct rtable *rt = NULL; if (skb != NULL) { - rt = skb->rtable; + rt = skb_rtable(skb); optptr = (unsigned char *)&(ip_hdr(skb)[1]); } else optptr = opt->__data; @@ -550,7 +550,7 @@ void ip_forward_options(struct sk_buff *skb) { struct ip_options * opt = &(IPCB(skb)->opt); unsigned char * optptr; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); unsigned char *raw = skb_network_header(skb); if (opt->rr_needaddr) { @@ -598,7 +598,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) __be32 nexthop; struct iphdr *iph = ip_hdr(skb); unsigned char *optptr = skb_network_header(skb) + opt->srr; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct rtable *rt2; int err; @@ -623,13 +623,13 @@ int ip_options_rcv_srr(struct sk_buff *skb) } memcpy(&nexthop, &optptr[srrptr-1], 4); - rt = skb->rtable; - skb->rtable = NULL; + rt = skb_rtable(skb); + skb->dst = NULL; err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); - rt2 = skb->rtable; + rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { ip_rt_put(rt2); - skb->rtable = rt; + skb->dst = &rt->u.dst; return -EINVAL; } ip_rt_put(rt); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ea19c37ccc0..8d845ebfcca 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -140,7 +140,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options *opt) { struct inet_sock *inet = inet_sk(sk); - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct iphdr *iph; /* Build the IP header. */ @@ -238,7 +238,7 @@ static int ip_finish_output(struct sk_buff *skb) int ip_mc_output(struct sk_buff *skb) { struct sock *sk = skb->sk; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->u.dst.dev; /* @@ -319,7 +319,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) /* Skip all of this if the packet is already routed, * f.e. by something like SCTP. */ - rt = skb->rtable; + rt = skb_rtable(skb); if (rt != NULL) goto packet_routed; @@ -440,7 +440,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) unsigned int mtu, hlen, left, len, ll_rs, pad; int offset; __be16 not_last_frag; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); int err = 0; dev = rt->u.dst.dev; @@ -1362,7 +1362,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar } replyopts; struct ipcm_cookie ipc; __be32 daddr; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); if (ip_options_echo(&replyopts.opt, skb)) return; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index cb49936856e..fc7993e9061 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -57,7 +57,7 @@ static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct in_pktinfo info; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); info.ipi_addr.s_addr = ip_hdr(skb)->daddr; if (rt) { diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index bb2f1b17fbf..0c6e7bf18a4 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -416,7 +416,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (!dst) { /* NBMA tunnel */ - if ((rt = skb->rtable) == NULL) { + if ((rt = skb_rtable(skb)) == NULL) { stats->tx_fifo_errors++; goto tx_error; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 13e9dd3012b..69dd058283e 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1354,7 +1354,7 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local if (net->ipv4.vif_table[vif].dev != skb->dev) { int true_vifi; - if (skb->rtable->fl.iif == 0) { + if (skb_rtable(skb)->fl.iif == 0) { /* It is our own packet, looped back. Very complicated situation... @@ -1430,7 +1430,7 @@ int ip_mr_input(struct sk_buff *skb) { struct mfc_cache *cache; struct net *net = dev_net(skb->dev); - int local = skb->rtable->rt_flags&RTCF_LOCAL; + int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; /* Packet is looped back after forward, it should not be forwarded second time, but still can be delivered locally. @@ -1646,7 +1646,7 @@ int ipmr_get_route(struct net *net, { int err; struct mfc_cache *cache; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); read_lock(&mrt_lock); cache = ipmr_cache_find(net, rt->rt_src, rt->rt_dst); diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index f389f60cb10..c0992c75bda 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -72,7 +72,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par) return NF_ACCEPT; mr = par->targinfo; - rt = skb->rtable; + rt = skb_rtable(skb); newsrc = inet_select_addr(par->out, rt->rt_gateway, RT_SCOPE_UNIVERSE); if (!newsrc) { printk("MASQUERADE: %s ate my IP address\n", par->out->name); diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index cf7a42bf982..155c008626c 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -140,7 +140,7 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct iphdr *iph; struct tcphdr *tcph; int oldlen, datalen; @@ -218,7 +218,7 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct iphdr *iph; struct udphdr *udph; int datalen, oldlen; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 28205e5bfa9..f20060ac2f0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1064,7 +1064,8 @@ work_done: out: return 0; } -static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp) +static int rt_intern_hash(unsigned hash, struct rtable *rt, + struct rtable **rp, struct sk_buff *skb) { struct rtable *rth, **rthp; unsigned long now; @@ -1114,7 +1115,10 @@ restart: spin_unlock_bh(rt_hash_lock_addr(hash)); rt_drop(rt); - *rp = rth; + if (rp) + *rp = rth; + else + skb->dst = &rth->u.dst; return 0; } @@ -1210,7 +1214,10 @@ restart: rcu_assign_pointer(rt_hash_table[hash].chain, rt); spin_unlock_bh(rt_hash_lock_addr(hash)); - *rp = rt; + if (rp) + *rp = rt; + else + skb->dst = &rt->u.dst; return 0; } @@ -1407,7 +1414,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, &netevent); rt_del(hash, rth); - if (!rt_intern_hash(hash, rt, &rt)) + if (!rt_intern_hash(hash, rt, &rt, NULL)) ip_rt_put(rt); goto do_next; } @@ -1473,7 +1480,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) void ip_rt_send_redirect(struct sk_buff *skb) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct in_device *in_dev = in_dev_get(rt->u.dst.dev); if (!in_dev) @@ -1521,7 +1528,7 @@ out: static int ip_error(struct sk_buff *skb) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); unsigned long now; int code; @@ -1698,7 +1705,7 @@ static void ipv4_link_failure(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); - rt = skb->rtable; + rt = skb_rtable(skb); if (rt) dst_set_expires(&rt->u.dst, 0); } @@ -1858,7 +1865,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, in_dev_put(in_dev); hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); - return rt_intern_hash(hash, rth, &skb->rtable); + return rt_intern_hash(hash, rth, NULL, skb); e_nobufs: in_dev_put(in_dev); @@ -2019,7 +2026,7 @@ static int ip_mkroute_input(struct sk_buff *skb, /* put it into the cache */ hash = rt_hash(daddr, saddr, fl->iif, rt_genid(dev_net(rth->u.dst.dev))); - return rt_intern_hash(hash, rth, &skb->rtable); + return rt_intern_hash(hash, rth, NULL, skb); } /* @@ -2175,7 +2182,7 @@ local_input: } rth->rt_type = res.type; hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net)); - err = rt_intern_hash(hash, rth, &skb->rtable); + err = rt_intern_hash(hash, rth, NULL, skb); goto done; no_route: @@ -2244,7 +2251,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, dst_use(&rth->u.dst, jiffies); RT_CACHE_STAT_INC(in_hit); rcu_read_unlock(); - skb->rtable = rth; + skb->dst = &rth->u.dst; return 0; } RT_CACHE_STAT_INC(in_hlist_search); @@ -2420,7 +2427,7 @@ static int ip_mkroute_output(struct rtable **rp, if (err == 0) { hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif, rt_genid(dev_net(dev_out))); - err = rt_intern_hash(hash, rth, rp); + err = rt_intern_hash(hash, rth, rp, NULL); } return err; @@ -2763,7 +2770,7 @@ static int rt_fill_info(struct net *net, struct sk_buff *skb, u32 pid, u32 seq, int event, int nowait, unsigned int flags) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; long expires; @@ -2907,7 +2914,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev); local_bh_enable(); - rt = skb->rtable; + rt = skb_rtable(skb); if (err == 0 && rt->u.dst.error) err = -rt->u.dst.error; } else { @@ -2927,7 +2934,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void if (err) goto errout_free; - skb->rtable = rt; + skb->dst = &rt->u.dst; if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fc79e341628..319c8852644 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -546,7 +546,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) if (th->rst) return; - if (skb->rtable->rt_type != RTN_LOCAL) + if (skb_rtable(skb)->rt_type != RTN_LOCAL) return; /* Swap the send and the receive. */ @@ -1185,7 +1185,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) #endif /* Never answer to SYNs send to broadcast or multicast */ - if (skb->rtable->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; /* TW buckets are converted to open requests without diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c index 8a3875e36ec..497b2224536 100644 --- a/net/netfilter/nf_conntrack_netbios_ns.c +++ b/net/netfilter/nf_conntrack_netbios_ns.c @@ -48,7 +48,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, { struct nf_conntrack_expect *exp; struct iphdr *iph = ip_hdr(skb); - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; __be32 mask = 0; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index fad596bf32d..b6b588bed4e 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -258,10 +258,10 @@ META_COLLECTOR(int_rtclassid) META_COLLECTOR(int_rtiif) { - if (unlikely(skb->rtable == NULL)) + if (unlikely(skb_rtable(skb) == NULL)) *err = -1; else - dst->value = skb->rtable->fl.iif; + dst->value = skb_rtable(skb)->fl.iif; } /************************************************************************** diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 8eb3e61cb70..cb2c50dbd42 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -393,7 +393,7 @@ static int sctp_v4_addr_valid(union sctp_addr *addr, return 0; /* Is this a broadcast address? */ - if (skb && skb->rtable->rt_flags & RTCF_BROADCAST) + if (skb && skb_rtable(skb)->rt_flags & RTCF_BROADCAST) return 0; return 1; @@ -572,7 +572,7 @@ static void sctp_v4_get_saddr(struct sctp_sock *sk, /* What interface did this skb arrive on? */ static int sctp_v4_skb_iif(const struct sk_buff *skb) { - return skb->rtable->rt_iif; + return skb_rtable(skb)->rt_iif; } /* Was this packet marked by Explicit Congestion Notification? */ @@ -848,8 +848,8 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb, skb->len, - &skb->rtable->rt_src, - &skb->rtable->rt_dst); + &skb_rtable(skb)->rt_src, + &skb_rtable(skb)->rt_dst); inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO : IP_PMTUDISC_DONT; -- cgit v1.2.3-70-g09d2 From adf30907d63893e4208dfe3f5c88ae12bc2f25d5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 2 Jun 2009 05:19:30 +0000 Subject: net: skb->dst accessors Define three accessors to get/set dst attached to a skb struct dst_entry *skb_dst(const struct sk_buff *skb) void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) void skb_dst_drop(struct sk_buff *skb) This one should replace occurrences of : dst_release(skb->dst) skb->dst = NULL; Delete skb->dst field Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 4 +- drivers/infiniband/ulp/ipoib/ipoib_main.c | 30 ++++++------- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 10 ++--- drivers/net/pppol2tp.c | 11 +++-- drivers/s390/net/qeth_core_main.c | 4 +- drivers/s390/net/qeth_l3_main.c | 8 ++-- include/linux/skbuff.h | 13 +++++- include/net/dst.h | 12 ++++-- include/net/inet6_hashtables.h | 2 +- include/net/inet_hashtables.h | 2 +- include/net/ip6_route.h | 2 +- include/net/xfrm.h | 4 +- net/atm/br2684.c | 2 +- net/atm/clip.c | 14 +++--- net/bridge/br_netfilter.c | 18 ++++---- net/core/dev.c | 7 ++- net/core/neighbour.c | 11 +++-- net/core/skbuff.c | 4 +- net/dccp/ipv4.c | 4 +- net/dccp/ipv6.c | 8 ++-- net/dccp/output.c | 2 +- net/decnet/af_decnet.c | 6 ++- net/decnet/dn_neigh.c | 8 ++-- net/decnet/dn_nsp_out.c | 6 +-- net/decnet/dn_route.c | 25 +++++------ net/ipv4/arp.c | 2 +- net/ipv4/icmp.c | 10 ++--- net/ipv4/igmp.c | 4 +- net/ipv4/ip_forward.c | 4 +- net/ipv4/ip_fragment.c | 2 +- net/ipv4/ip_gre.c | 23 +++++----- net/ipv4/ip_input.c | 6 +-- net/ipv4/ip_options.c | 6 +-- net/ipv4/ip_output.c | 20 ++++----- net/ipv4/ipip.c | 13 +++--- net/ipv4/ipmr.c | 13 +++--- net/ipv4/netfilter.c | 28 ++++++------ net/ipv4/netfilter/ipt_REJECT.c | 7 ++- net/ipv4/netfilter/nf_nat_standalone.c | 7 ++- net/ipv4/raw.c | 2 +- net/ipv4/route.c | 14 +++--- net/ipv4/tcp_ipv4.c | 4 +- net/ipv4/tcp_output.c | 2 +- net/ipv4/udp.c | 4 +- net/ipv4/xfrm4_input.c | 2 +- net/ipv4/xfrm4_mode_tunnel.c | 4 +- net/ipv4/xfrm4_output.c | 6 +-- net/ipv6/exthdrs.c | 40 ++++++++--------- net/ipv6/inet6_connection_sock.c | 2 +- net/ipv6/ip6_input.c | 12 +++--- net/ipv6/ip6_output.c | 60 +++++++++++++------------- net/ipv6/ip6_tunnel.c | 26 ++++++----- net/ipv6/ip6mr.c | 13 +++--- net/ipv6/mcast.c | 17 +++++--- net/ipv6/ndisc.c | 4 +- net/ipv6/netfilter.c | 16 ++++--- net/ipv6/netfilter/ip6t_REJECT.c | 2 +- net/ipv6/raw.c | 2 +- net/ipv6/reassembly.c | 22 +++++----- net/ipv6/route.c | 12 +++--- net/ipv6/sit.c | 21 +++++---- net/ipv6/tcp_ipv6.c | 8 ++-- net/ipv6/udp.c | 7 ++- net/ipv6/xfrm6_mode_tunnel.c | 4 +- net/ipv6/xfrm6_output.c | 4 +- net/netfilter/ipvs/ip_vs_xmit.c | 48 ++++++++++----------- net/netfilter/nf_conntrack_proto_gre.c | 2 +- net/netfilter/xt_TCPMSS.c | 6 +-- net/netfilter/xt_policy.c | 2 +- net/netfilter/xt_realm.c | 2 +- net/packet/af_packet.c | 6 +-- net/sched/cls_flow.c | 8 ++-- net/sched/cls_route.c | 2 +- net/sched/em_meta.c | 4 +- net/sched/sch_sfq.c | 2 +- net/sched/sch_teql.c | 6 +-- net/sctp/output.c | 6 +-- net/sunrpc/xprtsock.c | 2 +- net/xfrm/xfrm_input.c | 3 +- net/xfrm/xfrm_output.c | 21 ++++----- net/xfrm/xfrm_policy.c | 8 +++- security/selinux/hooks.c | 2 +- security/selinux/xfrm.c | 2 +- 83 files changed, 414 insertions(+), 390 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 4248c313936..181b1f32325 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1394,8 +1394,8 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb, struct ipoib_dev_priv *priv = netdev_priv(dev); int e = skb_queue_empty(&priv->cm.skb_queue); - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); skb_queue_tail(&priv->cm.skb_queue, skb); if (e) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 69c6304cc94..e319d91f60a 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -561,7 +561,7 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev) struct ipoib_neigh *neigh; unsigned long flags; - neigh = ipoib_neigh_alloc(skb->dst->neighbour, skb->dev); + neigh = ipoib_neigh_alloc(skb_dst(skb)->neighbour, skb->dev); if (!neigh) { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); @@ -570,9 +570,9 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev) spin_lock_irqsave(&priv->lock, flags); - path = __path_find(dev, skb->dst->neighbour->ha + 4); + path = __path_find(dev, skb_dst(skb)->neighbour->ha + 4); if (!path) { - path = path_rec_create(dev, skb->dst->neighbour->ha + 4); + path = path_rec_create(dev, skb_dst(skb)->neighbour->ha + 4); if (!path) goto err_path; @@ -605,7 +605,7 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev) goto err_drop; } } else - ipoib_send(dev, skb, path->ah, IPOIB_QPN(skb->dst->neighbour->ha)); + ipoib_send(dev, skb, path->ah, IPOIB_QPN(skb_dst(skb)->neighbour->ha)); } else { neigh->ah = NULL; @@ -635,15 +635,15 @@ static void ipoib_path_lookup(struct sk_buff *skb, struct net_device *dev) struct ipoib_dev_priv *priv = netdev_priv(skb->dev); /* Look up path record for unicasts */ - if (skb->dst->neighbour->ha[4] != 0xff) { + if (skb_dst(skb)->neighbour->ha[4] != 0xff) { neigh_add_path(skb, dev); return; } /* Add in the P_Key for multicasts */ - skb->dst->neighbour->ha[8] = (priv->pkey >> 8) & 0xff; - skb->dst->neighbour->ha[9] = priv->pkey & 0xff; - ipoib_mcast_send(dev, skb->dst->neighbour->ha + 4, skb); + skb_dst(skb)->neighbour->ha[8] = (priv->pkey >> 8) & 0xff; + skb_dst(skb)->neighbour->ha[9] = priv->pkey & 0xff; + ipoib_mcast_send(dev, skb_dst(skb)->neighbour->ha + 4, skb); } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, @@ -708,16 +708,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) struct ipoib_neigh *neigh; unsigned long flags; - if (likely(skb->dst && skb->dst->neighbour)) { - if (unlikely(!*to_ipoib_neigh(skb->dst->neighbour))) { + if (likely(skb_dst(skb) && skb_dst(skb)->neighbour)) { + if (unlikely(!*to_ipoib_neigh(skb_dst(skb)->neighbour))) { ipoib_path_lookup(skb, dev); return NETDEV_TX_OK; } - neigh = *to_ipoib_neigh(skb->dst->neighbour); + neigh = *to_ipoib_neigh(skb_dst(skb)->neighbour); if (unlikely((memcmp(&neigh->dgid.raw, - skb->dst->neighbour->ha + 4, + skb_dst(skb)->neighbour->ha + 4, sizeof(union ib_gid))) || (neigh->dev != dev))) { spin_lock_irqsave(&priv->lock, flags); @@ -743,7 +743,7 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } } else if (neigh->ah) { - ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(skb->dst->neighbour->ha)); + ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(skb_dst(skb)->neighbour->ha)); return NETDEV_TX_OK; } @@ -772,7 +772,7 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) if ((be16_to_cpup((__be16 *) skb->data) != ETH_P_ARP) && (be16_to_cpup((__be16 *) skb->data) != ETH_P_RARP)) { ipoib_warn(priv, "Unicast, no %s: type %04x, QPN %06x %pI6\n", - skb->dst ? "neigh" : "dst", + skb_dst(skb) ? "neigh" : "dst", be16_to_cpup((__be16 *) skb->data), IPOIB_QPN(phdr->hwaddr), phdr->hwaddr + 4); @@ -817,7 +817,7 @@ static int ipoib_hard_header(struct sk_buff *skb, * destination address onto the front of the skb so we can * figure out where to send the packet later. */ - if ((!skb->dst || !skb->dst->neighbour) && daddr) { + if ((!skb_dst(skb) || !skb_dst(skb)->neighbour) && daddr) { struct ipoib_pseudoheader *phdr = (struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr); memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 425e31112ed..a0e97532e71 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -261,7 +261,7 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast, skb->dev = dev; - if (!skb->dst || !skb->dst->neighbour) { + if (!skb_dst(skb) || !skb_dst(skb)->neighbour) { /* put pseudoheader back on for next time */ skb_push(skb, sizeof (struct ipoib_pseudoheader)); } @@ -707,10 +707,10 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb) out: if (mcast && mcast->ah) { - if (skb->dst && - skb->dst->neighbour && - !*to_ipoib_neigh(skb->dst->neighbour)) { - struct ipoib_neigh *neigh = ipoib_neigh_alloc(skb->dst->neighbour, + if (skb_dst(skb) && + skb_dst(skb)->neighbour && + !*to_ipoib_neigh(skb_dst(skb)->neighbour)) { + struct ipoib_neigh *neigh = ipoib_neigh_alloc(skb_dst(skb)->neighbour, skb->dev); if (neigh) { diff --git a/drivers/net/pppol2tp.c b/drivers/net/pppol2tp.c index 5981debcde5..e7935d09c89 100644 --- a/drivers/net/pppol2tp.c +++ b/drivers/net/pppol2tp.c @@ -433,8 +433,7 @@ static void pppol2tp_recv_dequeue_skb(struct pppol2tp_session *session, struct s * to the inner packet either */ secpath_reset(skb); - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); nf_reset(skb); po = pppox_sk(session_sock); @@ -976,7 +975,7 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh /* Calculate UDP checksum if configured to do so */ if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT) skb->ip_summed = CHECKSUM_NONE; - else if (!(skb->dst->dev->features & NETIF_F_V4_CSUM)) { + else if (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) { skb->ip_summed = CHECKSUM_COMPLETE; csum = skb_checksum(skb, 0, udp_len, 0); uh->check = csum_tcpudp_magic(inet->saddr, inet->daddr, @@ -1172,14 +1171,14 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) nf_reset(skb); /* Get routing info from the tunnel socket */ - dst_release(skb->dst); - skb->dst = dst_clone(__sk_dst_get(sk_tun)); + skb_dst_drop(skb); + skb_dst_set(skb, dst_clone(__sk_dst_get(sk_tun))); pppol2tp_skb_set_owner_w(skb, sk_tun); /* Calculate UDP checksum if configured to do so */ if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT) skb->ip_summed = CHECKSUM_NONE; - else if (!(skb->dst->dev->features & NETIF_F_V4_CSUM)) { + else if (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) { skb->ip_summed = CHECKSUM_COMPLETE; csum = skb_checksum(skb, 0, udp_len, 0); uh->check = csum_tcpudp_magic(inet->saddr, inet->daddr, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 2994aa1ed46..74c49d9a8db 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2937,8 +2937,8 @@ int qeth_get_cast_type(struct qeth_card *card, struct sk_buff *skb) if (card->info.type == QETH_CARD_TYPE_OSN) return cast_type; - if (skb->dst && skb->dst->neighbour) { - cast_type = skb->dst->neighbour->type; + if (skb_dst(skb) && skb_dst(skb)->neighbour) { + cast_type = skb_dst(skb)->neighbour->type; if ((cast_type == RTN_BROADCAST) || (cast_type == RTN_MULTICAST) || (cast_type == RTN_ANYCAST)) diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index cb64b0b534a..6f2386e9d6e 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2549,9 +2549,9 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, /* IPv4 */ hdr->hdr.l3.flags = qeth_l3_get_qeth_hdr_flags4(cast_type); memset(hdr->hdr.l3.dest_addr, 0, 12); - if ((skb->dst) && (skb->dst->neighbour)) { + if ((skb_dst(skb)) && (skb_dst(skb)->neighbour)) { *((u32 *) (&hdr->hdr.l3.dest_addr[12])) = - *((u32 *) skb->dst->neighbour->primary_key); + *((u32 *) skb_dst(skb)->neighbour->primary_key); } else { /* fill in destination address used in ip header */ *((u32 *) (&hdr->hdr.l3.dest_addr[12])) = @@ -2562,9 +2562,9 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, hdr->hdr.l3.flags = qeth_l3_get_qeth_hdr_flags6(cast_type); if (card->info.type == QETH_CARD_TYPE_IQD) hdr->hdr.l3.flags &= ~QETH_HDR_PASSTHRU; - if ((skb->dst) && (skb->dst->neighbour)) { + if ((skb_dst(skb)) && (skb_dst(skb)->neighbour)) { memcpy(hdr->hdr.l3.dest_addr, - skb->dst->neighbour->primary_key, 16); + skb_dst(skb)->neighbour->primary_key, 16); } else { /* fill in destination address used in ip header */ memcpy(hdr->hdr.l3.dest_addr, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a3ae3c52583..9ef6eb20247 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -323,7 +323,6 @@ struct sk_buff { struct net_device *dev; union { - struct dst_entry *dst; unsigned long _skb_dst; }; #ifdef CONFIG_XFRM @@ -426,9 +425,19 @@ extern void skb_dma_unmap(struct device *dev, struct sk_buff *skb, enum dma_data_direction dir); #endif +static inline struct dst_entry *skb_dst(const struct sk_buff *skb) +{ + return (struct dst_entry *)skb->_skb_dst; +} + +static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) +{ + skb->_skb_dst = (unsigned long)dst; +} + static inline struct rtable *skb_rtable(const struct sk_buff *skb) { - return (struct rtable *)skb->_skb_dst; + return (struct rtable *)skb_dst(skb); } extern void kfree_skb(struct sk_buff *skb); diff --git a/include/net/dst.h b/include/net/dst.h index 6be3b082a07..7fc409c19b3 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -195,6 +195,12 @@ struct dst_entry * dst_clone(struct dst_entry * dst) } extern void dst_release(struct dst_entry *dst); +static inline void skb_dst_drop(struct sk_buff *skb) +{ + if (skb->_skb_dst) + dst_release(skb_dst(skb)); + skb->_skb_dst = 0UL; +} /* Children define the path of the packet through the * Linux networking. Thus, destinations are stackable. @@ -246,7 +252,7 @@ static inline void dst_negative_advice(struct dst_entry **dst_p) static inline void dst_link_failure(struct sk_buff *skb) { - struct dst_entry * dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops && dst->ops->link_failure) dst->ops->link_failure(skb); } @@ -265,13 +271,13 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) /* Output packet to network from transport. */ static inline int dst_output(struct sk_buff *skb) { - return skb->dst->output(skb); + return skb_dst(skb)->output(skb); } /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) { - return skb->dst->input(skb); + return skb_dst(skb)->input(skb); } static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index f74665d7bea..22c73a77cd9 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -100,7 +100,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, if (unlikely(sk = skb_steal_sock(skb))) return sk; - else return __inet6_lookup(dev_net(skb->dst->dev), hashinfo, + else return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, &ipv6_hdr(skb)->saddr, sport, &ipv6_hdr(skb)->daddr, ntohs(dport), inet6_iif(skb)); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index a44e2248b2e..d522dcf3031 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -385,7 +385,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, if (unlikely(sk = skb_steal_sock(skb))) return sk; else - return __inet_lookup(dev_net(skb->dst->dev), hashinfo, + return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, iph->saddr, sport, iph->daddr, dport, inet_iif(skb)); } diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 5f53db7e4e5..0e1b8aebaff 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -142,7 +142,7 @@ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, static inline int ipv6_unicast_destination(struct sk_buff *skb) { - struct rt6_info *rt = (struct rt6_info *) skb->dst; + struct rt6_info *rt = (struct rt6_info *) skb_dst(skb); return rt->rt6i_flags & RTF_LOCAL; } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 2e9f5c0018a..736bca45088 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -994,7 +994,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, return __xfrm_policy_check(sk, ndir, skb, family); return (!net->xfrm.policy_count[dir] && !skb->sp) || - (skb->dst->flags & DST_NOPOLICY) || + (skb_dst(skb)->flags & DST_NOPOLICY) || __xfrm_policy_check(sk, ndir, skb, family); } @@ -1048,7 +1048,7 @@ static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family) struct net *net = dev_net(skb->dev); return !net->xfrm.policy_count[XFRM_POLICY_OUT] || - (skb->dst->flags & DST_NOXFRM) || + (skb_dst(skb)->flags & DST_NOXFRM) || __xfrm_route_forward(skb, family); } diff --git a/net/atm/br2684.c b/net/atm/br2684.c index bfa8fa9894f..2912665fc58 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -228,7 +228,7 @@ static int br2684_start_xmit(struct sk_buff *skb, struct net_device *dev) struct br2684_dev *brdev = BRPRIV(dev); struct br2684_vcc *brvcc; - pr_debug("br2684_start_xmit, skb->dst=%p\n", skb->dst); + pr_debug("br2684_start_xmit, skb_dst(skb)=%p\n", skb_dst(skb)); read_lock(&devs_lock); brvcc = pick_outgoing_vcc(skb, brdev); if (brvcc == NULL) { diff --git a/net/atm/clip.c b/net/atm/clip.c index fb7623c080f..e65a3b1477f 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -369,16 +369,16 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned long flags; pr_debug("clip_start_xmit (skb %p)\n", skb); - if (!skb->dst) { - printk(KERN_ERR "clip_start_xmit: skb->dst == NULL\n"); + if (!skb_dst(skb)) { + printk(KERN_ERR "clip_start_xmit: skb_dst(skb) == NULL\n"); dev_kfree_skb(skb); dev->stats.tx_dropped++; return 0; } - if (!skb->dst->neighbour) { + if (!skb_dst(skb)->neighbour) { #if 0 - skb->dst->neighbour = clip_find_neighbour(skb->dst, 1); - if (!skb->dst->neighbour) { + skb_dst(skb)->neighbour = clip_find_neighbour(skb_dst(skb), 1); + if (!skb_dst(skb)->neighbour) { dev_kfree_skb(skb); /* lost that one */ dev->stats.tx_dropped++; return 0; @@ -389,7 +389,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_dropped++; return 0; } - entry = NEIGH2ENTRY(skb->dst->neighbour); + entry = NEIGH2ENTRY(skb_dst(skb)->neighbour); if (!entry->vccs) { if (time_after(jiffies, entry->expires)) { /* should be resolved */ @@ -406,7 +406,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) } pr_debug("neigh %p, vccs %p\n", entry, entry->vccs); ATM_SKB(skb)->vcc = vcc = entry->vccs->vcc; - pr_debug("using neighbour %p, vcc %p\n", skb->dst->neighbour, vcc); + pr_debug("using neighbour %p, vcc %p\n", skb_dst(skb)->neighbour, vcc); if (entry->vccs->encap) { void *here; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index e0ceb66a9ec..d22f611e400 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -242,7 +242,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) return 0; } dst_hold(&rt->u.dst); - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); skb->dev = nf_bridge->physindev; nf_bridge_push_encap_header(skb); @@ -322,7 +322,7 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) skb->dev = bridge_parent(skb->dev); if (skb->dev) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); nf_bridge_pull_encap_header(skb); @@ -375,7 +375,7 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) /* - Bridged-and-DNAT'ed traffic doesn't * require ip_forwarding. */ if (((struct dst_entry *)rt)->dev == dev) { - skb->dst = (struct dst_entry *)rt; + skb_dst_set(skb, (struct dst_entry *)rt); goto bridged_dnat; } /* we are sure that forwarding is disabled, so printing @@ -389,7 +389,7 @@ free_skb: kfree_skb(skb); return 0; } else { - if (skb->dst->dev == dev) { + if (skb_dst(skb)->dev == dev) { bridged_dnat: /* Tell br_nf_local_out this is a * bridged frame */ @@ -412,7 +412,7 @@ bridged_dnat: return 0; } dst_hold(&rt->u.dst); - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); } skb->dev = nf_bridge->physindev; @@ -633,10 +633,8 @@ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb, { struct rtable *rt = skb_rtable(skb); - if (rt && rt == bridge_parent_rtable(in)) { - dst_release(&rt->u.dst); - skb->dst = NULL; - } + if (rt && rt == bridge_parent_rtable(in)) + skb_dst_drop(skb); return NF_ACCEPT; } @@ -851,7 +849,7 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, return NF_ACCEPT; #ifdef CONFIG_NETFILTER_DEBUG - if (skb->dst == NULL) { + if (skb_dst(skb) == NULL) { printk(KERN_INFO "br_netfilter post_routing: skb->dst == NULL\n"); goto print_error; } diff --git a/net/core/dev.c b/net/core/dev.c index e2fcc5f1017..34b49a6a22f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1693,10 +1693,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, * If device doesnt need skb->dst, release it right now while * its hot in this cpu cache */ - if ((dev->priv_flags & IFF_XMIT_DST_RELEASE) && skb->dst) { - dst_release(skb->dst); - skb->dst = NULL; - } + if (dev->priv_flags & IFF_XMIT_DST_RELEASE) + skb_dst_drop(skb); + rc = ops->ndo_start_xmit(skb, dev); if (rc == 0) txq_trans_update(txq); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a1cbce7fdae..c54229befcf 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1088,8 +1088,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, struct neighbour *n1 = neigh; write_unlock_bh(&neigh->lock); /* On shaper/eql skb->dst->neighbour != neigh :( */ - if (skb->dst && skb->dst->neighbour) - n1 = skb->dst->neighbour; + if (skb_dst(skb) && skb_dst(skb)->neighbour) + n1 = skb_dst(skb)->neighbour; n1->output(skb); write_lock_bh(&neigh->lock); } @@ -1182,7 +1182,7 @@ EXPORT_SYMBOL(neigh_compat_output); int neigh_resolve_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh; int rc = 0; @@ -1229,7 +1229,7 @@ EXPORT_SYMBOL(neigh_resolve_output); int neigh_connected_output(struct sk_buff *skb) { int err; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; @@ -1298,8 +1298,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, if (time_before(tbl->proxy_timer.expires, sched_next)) sched_next = tbl->proxy_timer.expires; } - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); dev_hold(skb->dev); __skb_queue_tail(&tbl->proxy_queue, skb); mod_timer(&tbl->proxy_timer, sched_next); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8e815e685f2..6adf19ec95c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -381,7 +381,7 @@ static void kfree_skbmem(struct sk_buff *skb) static void skb_release_head_state(struct sk_buff *skb) { - dst_release(skb->dst); + skb_dst_drop(skb); #ifdef CONFIG_XFRM secpath_put(skb->sp); #endif @@ -521,7 +521,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->transport_header = old->transport_header; new->network_header = old->network_header; new->mac_header = old->mac_header; - new->dst = dst_clone(old->dst); + skb_dst_set(new, dst_clone(skb_dst(old))); #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 2cf48ba0dbb..a0a36c9e6cc 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -507,7 +507,7 @@ static void dccp_v4_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) const struct iphdr *rxiph; struct sk_buff *skb; struct dst_entry *dst; - struct net *net = dev_net(rxskb->dst->dev); + struct net *net = dev_net(skb_dst(rxskb)->dev); struct sock *ctl_sk = net->dccp.v4_ctl_sk; /* Never send a reset in response to a reset. */ @@ -528,7 +528,7 @@ static void dccp_v4_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) rxiph = ip_hdr(rxskb); dccp_hdr(skb)->dccph_checksum = dccp_v4_csum_finish(skb, rxiph->saddr, rxiph->daddr); - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); bh_lock_sock(ctl_sk); err = ip_build_and_send_pkt(skb, ctl_sk, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index b963f35c65f..05ea7440d9e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -314,8 +314,9 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) struct ipv6hdr *rxip6h; struct sk_buff *skb; struct flowi fl; - struct net *net = dev_net(rxskb->dst->dev); + struct net *net = dev_net(skb_dst(rxskb)->dev); struct sock *ctl_sk = net->dccp.v6_ctl_sk; + struct dst_entry *dst; if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; @@ -342,8 +343,9 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) security_skb_classify_flow(rxskb, &fl); /* sk = NULL, but it is safe for now. RST socket required. */ - if (!ip6_dst_lookup(ctl_sk, &skb->dst, &fl)) { - if (xfrm_lookup(net, &skb->dst, &fl, NULL, 0) >= 0) { + if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) { + if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { + skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl, NULL, 0); DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); diff --git a/net/dccp/output.c b/net/dccp/output.c index 36bcc00654d..c0e88c16d08 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -350,7 +350,7 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, /* Reserve space for headers. */ skb_reserve(skb, sk->sk_prot->max_header); - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); dreq = dccp_rsk(req); if (inet_rsk(req)->acked) /* increase ISS upon retransmission */ diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index bccb3887773..a5e3a593e47 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1075,6 +1075,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) int err = 0; unsigned char type; long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + struct dst_entry *dst; lock_sock(sk); @@ -1102,8 +1103,9 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) } release_sock(sk); - dst_release(xchg(&newsk->sk_dst_cache, skb->dst)); - skb->dst = NULL; + dst = skb_dst(skb); + dst_release(xchg(&newsk->sk_dst_cache, dst)); + skb_dst_set(skb, NULL); DN_SK(newsk)->state = DN_CR; DN_SK(newsk)->addrrem = cb->src_port; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 05b5aa05e50..923786bd6d0 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -204,7 +204,7 @@ static void dn_short_error_report(struct neighbour *neigh, struct sk_buff *skb) static int dn_neigh_output_packet(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; @@ -224,7 +224,7 @@ static int dn_neigh_output_packet(struct sk_buff *skb) static int dn_long_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_long_packet) + 3; @@ -270,7 +270,7 @@ static int dn_long_output(struct sk_buff *skb) static int dn_short_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; @@ -313,7 +313,7 @@ static int dn_short_output(struct sk_buff *skb) */ static int dn_phase3_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index da04f459337..a65e929ce76 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -85,7 +85,7 @@ static void dn_nsp_send(struct sk_buff *skb) dst = sk_dst_check(sk, 0); if (dst) { try_again: - skb->dst = dst; + skb_dst_set(skb, dst); dst_output(skb); return; } @@ -582,7 +582,7 @@ static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, * to be able to send disc packets out which have no socket * associations. */ - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); dst_output(skb); } @@ -611,7 +611,7 @@ void dn_nsp_return_disc(struct sk_buff *skb, unsigned char msgflg, int ddl = 0; gfp_t gfp = GFP_ATOMIC; - dn_nsp_do_disc(NULL, msgflg, reason, gfp, skb->dst, ddl, + dn_nsp_do_disc(NULL, msgflg, reason, gfp, skb_dst(skb), ddl, NULL, cb->src_port, cb->dst_port); } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 0cc4394117d..1d6ca8a98dc 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -678,7 +678,7 @@ out: static int dn_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; struct net_device *dev = dst->dev; struct dn_skb_cb *cb = DN_SKB_CB(skb); @@ -717,7 +717,7 @@ error: static int dn_forward(struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct dn_dev *dn_db = dst->dev->dn_ptr; struct dn_route *rt; struct neighbour *neigh = dst->neighbour; @@ -730,7 +730,7 @@ static int dn_forward(struct sk_buff *skb) goto drop; /* Ensure that we have enough space for headers */ - rt = (struct dn_route *)skb->dst; + rt = (struct dn_route *)skb_dst(skb); header_len = dn_db->use_long ? 21 : 6; if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+header_len)) goto drop; @@ -1392,7 +1392,8 @@ make_route: goto e_neighbour; hash = dn_hash(rt->fl.fld_src, rt->fl.fld_dst); - dn_insert_route(rt, hash, (struct dn_route **)&skb->dst); + dn_insert_route(rt, hash, &rt); + skb_dst_set(skb, &rt->u.dst); done: if (neigh) @@ -1424,7 +1425,7 @@ static int dn_route_input(struct sk_buff *skb) struct dn_skb_cb *cb = DN_SKB_CB(skb); unsigned hash = dn_hash(cb->src, cb->dst); - if (skb->dst) + if (skb_dst(skb)) return 0; rcu_read_lock(); @@ -1437,7 +1438,7 @@ static int dn_route_input(struct sk_buff *skb) (rt->fl.iif == cb->iif)) { dst_use(&rt->u.dst, jiffies); rcu_read_unlock(); - skb->dst = (struct dst_entry *)rt; + skb_dst_set(skb, (struct dst_entry *)rt); return 0; } } @@ -1449,7 +1450,7 @@ static int dn_route_input(struct sk_buff *skb) static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, int nowait, unsigned int flags) { - struct dn_route *rt = (struct dn_route *)skb->dst; + struct dn_route *rt = (struct dn_route *)skb_dst(skb); struct rtmsg *r; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); @@ -1554,7 +1555,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void err = dn_route_input(skb); local_bh_enable(); memset(cb, 0, sizeof(struct dn_skb_cb)); - rt = (struct dn_route *)skb->dst; + rt = (struct dn_route *)skb_dst(skb); if (!err && -rt->u.dst.error) err = rt->u.dst.error; } else { @@ -1570,7 +1571,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void skb->dev = NULL; if (err) goto out_free; - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; @@ -1622,15 +1623,15 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) rt = rcu_dereference(rt->u.dst.dn_next), idx++) { if (idx < s_idx) continue; - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1, NLM_F_MULTI) <= 0) { - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); rcu_read_unlock_bh(); goto done; } - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); } rcu_read_unlock_bh(); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 816494f271a..8a3881e28ac 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -468,7 +468,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb) __be32 paddr; struct neighbour *n; - if (!skb->dst) { + if (!skb_dst(skb)) { printk(KERN_DEBUG "arp_find is called with dst==NULL\n"); kfree_skb(skb); return 1; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 94f75efae93..97c410e8438 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -591,13 +591,13 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) goto relookup_failed; /* Ugh! */ - odst = skb_in->dst; + odst = skb_dst(skb_in); err = ip_route_input(skb_in, fl.fl4_dst, fl.fl4_src, RT_TOS(tos), rt2->u.dst.dev); dst_release(&rt2->u.dst); rt2 = skb_rtable(skb_in); - skb_in->dst = odst; + skb_dst_set(skb_in, odst); } if (err) @@ -659,7 +659,7 @@ static void icmp_unreach(struct sk_buff *skb) u32 info = 0; struct net *net; - net = dev_net(skb->dst->dev); + net = dev_net(skb_dst(skb)->dev); /* * Incomplete header ? @@ -822,7 +822,7 @@ static void icmp_echo(struct sk_buff *skb) { struct net *net; - net = dev_net(skb->dst->dev); + net = dev_net(skb_dst(skb)->dev); if (!net->ipv4.sysctl_icmp_echo_ignore_all) { struct icmp_bxm icmp_param; @@ -873,7 +873,7 @@ static void icmp_timestamp(struct sk_buff *skb) out: return; out_err: - ICMP_INC_STATS_BH(dev_net(skb->dst->dev), ICMP_MIB_INERRORS); + ICMP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS); goto out; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index afabd2758b6..01b4284ed69 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -311,7 +311,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) return NULL; } - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); skb->dev = dev; skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -659,7 +659,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, return -1; } - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); skb_reserve(skb, LL_RESERVED_SPACE(dev)); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 0761cd9bbd1..a2991bc8e32 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -42,7 +42,7 @@ static int ip_forward_finish(struct sk_buff *skb) { struct ip_options * opt = &(IPCB(skb)->opt); - IP_INC_STATS_BH(dev_net(skb->dst->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); if (unlikely(opt->optlen)) ip_forward_options(skb); @@ -123,7 +123,7 @@ sr_failed: too_many_hops: /* Tell the sender its packet died... */ - IP_INC_STATS_BH(dev_net(skb->dst->dev), IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); drop: kfree_skb(skb); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 7985346653b..1f1b82475ea 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -573,7 +573,7 @@ int ip_defrag(struct sk_buff *skb, u32 user) struct ipq *qp; struct net *net; - net = skb->dev ? dev_net(skb->dev) : dev_net(skb->dst->dev); + net = skb->dev ? dev_net(skb->dev) : dev_net(skb_dst(skb)->dev); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); /* Start by cleaning up the memory. */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 85ddad45a91..44e2a3d2359 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -643,8 +643,7 @@ static int ipgre_rcv(struct sk_buff *skb) stats->rx_packets++; stats->rx_bytes += len; skb->dev = tunnel->dev; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); nf_reset(skb); skb_reset_network_header(skb); @@ -698,7 +697,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if ((dst = tiph->daddr) == 0) { /* NBMA tunnel */ - if (skb->dst == NULL) { + if (skb_dst(skb) == NULL) { stats->tx_fifo_errors++; goto tx_error; } @@ -712,7 +711,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) else if (skb->protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; int addr_type; - struct neighbour *neigh = skb->dst->neighbour; + struct neighbour *neigh = skb_dst(skb)->neighbour; if (neigh == NULL) goto tx_error; @@ -766,10 +765,10 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (df) mtu = dst_mtu(&rt->u.dst) - dev->hard_header_len - tunnel->hlen; else - mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu; + mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (skb->protocol == htons(ETH_P_IP)) { df |= (old_iph->frag_off&htons(IP_DF)); @@ -783,14 +782,14 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } #ifdef CONFIG_IPV6 else if (skb->protocol == htons(ETH_P_IPV6)) { - struct rt6_info *rt6 = (struct rt6_info *)skb->dst; + struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); - if (rt6 && mtu < dst_mtu(skb->dst) && mtu >= IPV6_MIN_MTU) { + if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) { if ((tunnel->parms.iph.daddr && !ipv4_is_multicast(tunnel->parms.iph.daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; - skb->dst->metrics[RTAX_MTU-1] = mtu; + skb_dst(skb)->metrics[RTAX_MTU-1] = mtu; } } @@ -837,8 +836,8 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index cea784b0aa4..490ce20faf3 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -329,7 +329,7 @@ static int ip_rcv_finish(struct sk_buff *skb) * Initialise the virtual path cache for the packet. It describes * how the packet travels inside Linux networking. */ - if (skb->dst == NULL) { + if (skb_dst(skb) == NULL) { int err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, skb->dev); if (unlikely(err)) { @@ -344,9 +344,9 @@ static int ip_rcv_finish(struct sk_buff *skb) } #ifdef CONFIG_NET_CLS_ROUTE - if (unlikely(skb->dst->tclassid)) { + if (unlikely(skb_dst(skb)->tclassid)) { struct ip_rt_acct *st = per_cpu_ptr(ip_rt_acct, smp_processor_id()); - u32 idx = skb->dst->tclassid; + u32 idx = skb_dst(skb)->tclassid; st[idx&0xFF].o_packets++; st[idx&0xFF].o_bytes += skb->len; st[(idx>>16)&0xFF].i_packets++; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 7e1074ffdbd..94bf105ef3c 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -143,7 +143,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) __be32 addr; memcpy(&addr, sptr+soffset-1, 4); - if (inet_addr_type(dev_net(skb->dst->dev), addr) != RTN_LOCAL) { + if (inet_addr_type(dev_net(skb_dst(skb)->dev), addr) != RTN_LOCAL) { dopt->ts_needtime = 1; soffset += 8; } @@ -624,12 +624,12 @@ int ip_options_rcv_srr(struct sk_buff *skb) memcpy(&nexthop, &optptr[srrptr-1], 4); rt = skb_rtable(skb); - skb->dst = NULL; + skb_dst_set(skb, NULL); err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { ip_rt_put(rt2); - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); return -EINVAL; } ip_rt_put(rt); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8d845ebfcca..3d6167fb2d9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -95,7 +95,7 @@ int __ip_local_out(struct sk_buff *skb) iph->tot_len = htons(skb->len); ip_send_check(iph); - return nf_hook(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, skb->dst->dev, + return nf_hook(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev, dst_output); } @@ -118,7 +118,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb) __skb_pull(newskb, skb_network_offset(newskb)); newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!newskb->dst); + WARN_ON(!skb_dst(newskb)); netif_rx(newskb); return 0; } @@ -176,7 +176,7 @@ EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static inline int ip_finish_output2(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); @@ -217,14 +217,14 @@ static inline int ip_skb_dst_mtu(struct sk_buff *skb) struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL; return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ? - skb->dst->dev->mtu : dst_mtu(skb->dst); + skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); } static int ip_finish_output(struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ - if (skb->dst->xfrm != NULL) { + if (skb_dst(skb)->xfrm != NULL) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(skb); } @@ -296,7 +296,7 @@ int ip_mc_output(struct sk_buff *skb) int ip_output(struct sk_buff *skb) { - struct net_device *dev = skb->dst->dev; + struct net_device *dev = skb_dst(skb)->dev; IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); @@ -355,7 +355,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) } sk_setup_caps(sk, &rt->u.dst); } - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); packet_routed: if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) @@ -401,8 +401,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; - dst_release(to->dst); - to->dst = dst_clone(from->dst); + skb_dst_drop(to); + skb_dst_set(to, dst_clone(skb_dst(from))); to->dev = from->dev; to->mark = from->mark; @@ -1294,7 +1294,7 @@ int ip_push_pending_frames(struct sock *sk) * on dst refcount */ inet->cork.dst = NULL; - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); if (iph->protocol == IPPROTO_ICMP) icmp_out_count(net, ((struct icmphdr *) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 0c6e7bf18a4..93e2b787da2 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -370,8 +370,7 @@ static int ipip_rcv(struct sk_buff *skb) tunnel->dev->stats.rx_packets++; tunnel->dev->stats.rx_bytes += skb->len; skb->dev = tunnel->dev; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); nf_reset(skb); ipip_ecn_decapsulate(iph, skb); netif_rx(skb); @@ -447,15 +446,15 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (tiph->frag_off) mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); else - mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu; + mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (mtu < 68) { stats->collisions++; ip_rt_put(rt); goto tx_error; } - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); df |= (old_iph->frag_off&htons(IP_DF)); @@ -502,8 +501,8 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 69dd058283e..ffd98610446 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -651,7 +651,7 @@ static int ipmr_cache_report(struct net *net, ip_hdr(skb)->protocol = 0; /* Flag to the kernel this is a route add */ msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; - skb->dst = dst_clone(pkt->dst); + skb_dst_set(skb, dst_clone(skb_dst(pkt))); /* * Add our header @@ -1201,7 +1201,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(iph, skb->dst, NULL); + ip_select_ident(iph, skb_dst(skb), NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -1212,7 +1212,7 @@ static inline int ipmr_forward_finish(struct sk_buff *skb) { struct ip_options * opt = &(IPCB(skb)->opt); - IP_INC_STATS_BH(dev_net(skb->dst->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); if (unlikely(opt->optlen)) ip_forward_options(skb); @@ -1290,8 +1290,8 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi) vif->pkt_out++; vif->bytes_out += skb->len; - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); ip_decrease_ttl(ip_hdr(skb)); /* FIXME: forward and output firewalls used to be called here. @@ -1543,8 +1543,7 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen) skb->protocol = htons(ETH_P_IP); skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); reg_dev->stats.rx_bytes += skb->len; reg_dev->stats.rx_packets++; nf_reset(skb); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index fdf6811c31a..1725dc0ef68 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -12,7 +12,7 @@ /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) { - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi fl = {}; @@ -41,8 +41,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) return -1; /* Drop old route. */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); } else { /* non-local src, find valid iif to satisfy * rp-filter when calling ip_route_input. */ @@ -50,7 +50,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) if (ip_route_output_key(net, &rt, &fl) != 0) return -1; - odst = skb->dst; + odst = skb_dst(skb); if (ip_route_input(skb, iph->daddr, iph->saddr, RT_TOS(iph->tos), rt->u.dst.dev) != 0) { dst_release(&rt->u.dst); @@ -60,18 +60,22 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) dst_release(odst); } - if (skb->dst->error) + if (skb_dst(skb)->error) return -1; #ifdef CONFIG_XFRM if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && - xfrm_decode_session(skb, &fl, AF_INET) == 0) - if (xfrm_lookup(net, &skb->dst, &fl, skb->sk, 0)) + xfrm_decode_session(skb, &fl, AF_INET) == 0) { + struct dst_entry *dst = skb_dst(skb); + skb_dst_set(skb, NULL); + if (xfrm_lookup(net, &dst, &fl, skb->sk, 0)) return -1; + skb_dst_set(skb, dst); + } #endif /* Change in oif may mean change in hh_len. */ - hh_len = skb->dst->dev->hard_header_len; + hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) return -1; @@ -92,7 +96,7 @@ int ip_xfrm_me_harder(struct sk_buff *skb) if (xfrm_decode_session(skb, &fl, AF_INET) < 0) return -1; - dst = skb->dst; + dst = skb_dst(skb); if (dst->xfrm) dst = ((struct xfrm_dst *)dst)->route; dst_hold(dst); @@ -100,11 +104,11 @@ int ip_xfrm_me_harder(struct sk_buff *skb) if (xfrm_lookup(dev_net(dst->dev), &dst, &fl, skb->sk, 0) < 0) return -1; - dst_release(skb->dst); - skb->dst = dst; + skb_dst_drop(skb); + skb_dst_set(skb, dst); /* Change in oif may mean change in hh_len. */ - hh_len = skb->dst->dev->hard_header_len; + hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) return -1; diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 0b4b6e0ff2b..c93ae44bff2 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -108,17 +108,16 @@ static void send_reset(struct sk_buff *oldskb, int hook) addr_type = RTN_LOCAL; /* ip_route_me_harder expects skb->dst to be set */ - dst_hold(oldskb->dst); - nskb->dst = oldskb->dst; + skb_dst_set(nskb, dst_clone(skb_dst(oldskb))); if (ip_route_me_harder(nskb, addr_type)) goto free_nskb; - niph->ttl = dst_metric(nskb->dst, RTAX_HOPLIMIT); + niph->ttl = dst_metric(skb_dst(nskb), RTAX_HOPLIMIT); nskb->ip_summed = CHECKSUM_NONE; /* "Never happens" */ - if (nskb->len > dst_mtu(nskb->dst)) + if (nskb->len > dst_mtu(skb_dst(nskb))) goto free_nskb; nf_ct_attach(nskb, oldskb); diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index b7dd695691a..5567bd0d075 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -167,10 +167,9 @@ nf_nat_in(unsigned int hooknum, ret = nf_nat_fn(hooknum, skb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN && - daddr != ip_hdr(skb)->daddr) { - dst_release(skb->dst); - skb->dst = NULL; - } + daddr != ip_hdr(skb)->daddr) + skb_dst_drop(skb); + return ret; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index f774651f0a4..3dc9171a272 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -343,7 +343,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); skb_reset_network_header(skb); iph = ip_hdr(skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f20060ac2f0..a849bb15d86 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1118,7 +1118,7 @@ restart: if (rp) *rp = rth; else - skb->dst = &rth->u.dst; + skb_dst_set(skb, &rth->u.dst); return 0; } @@ -1217,7 +1217,7 @@ restart: if (rp) *rp = rt; else - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); return 0; } @@ -2251,7 +2251,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, dst_use(&rth->u.dst, jiffies); RT_CACHE_STAT_INC(in_hit); rcu_read_unlock(); - skb->dst = &rth->u.dst; + skb_dst_set(skb, &rth->u.dst); return 0; } RT_CACHE_STAT_INC(in_hlist_search); @@ -2934,7 +2934,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void if (err) goto errout_free; - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; @@ -2975,15 +2975,15 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; if (rt_is_expired(rt)) continue; - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1, NLM_F_MULTI) <= 0) { - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); rcu_read_unlock_bh(); goto done; } - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); } rcu_read_unlock_bh(); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 319c8852644..5a1ca2698c8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -590,7 +590,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; - net = dev_net(skb->dst->dev); + net = dev_net(skb_dst(skb)->dev); ip_send_reply(net->ipv4.tcp_sock, skb, &arg, arg.iov[0].iov_len); @@ -617,7 +617,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, ]; } rep; struct ip_reply_arg arg; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 79c39dc9b01..416fc4c2e7e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2202,7 +2202,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); mss = dst_metric(dst, RTAX_ADVMSS); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7a1d1ce22e6..8f4158d7c9a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -328,7 +328,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, if (unlikely(sk = skb_steal_sock(skb))) return sk; else - return __udp4_lib_lookup(dev_net(skb->dst->dev), iph->saddr, sport, + return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), udptable); } @@ -1237,7 +1237,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct sock *sk; struct udphdr *uh; unsigned short ulen; - struct rtable *rt = (struct rtable*)skb->dst; + struct rtable *rt = skb_rtable(skb); __be32 saddr, daddr; struct net *net = dev_net(skb->dev); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 4ec2162a437..f9f922a0ba8 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -23,7 +23,7 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb) static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) { - if (skb->dst == NULL) { + if (skb_dst(skb) == NULL) { const struct iphdr *iph = ip_hdr(skb); if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 7135279f3f8..3444f3b34ec 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -28,7 +28,7 @@ static inline void ipip_ecn_decapsulate(struct sk_buff *skb) */ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct iphdr *top_iph; int flags; @@ -41,7 +41,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->ihl = 5; top_iph->version = 4; - top_iph->protocol = xfrm_af2proto(skb->dst->ops->family); + top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family); /* DS disclosed */ top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos, diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 8c3180adddb..c908bd99bcb 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -29,7 +29,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->local_df) goto out; - dst = skb->dst; + dst = skb_dst(skb); mtu = dst_mtu(dst); if (skb->len > mtu) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); @@ -72,7 +72,7 @@ EXPORT_SYMBOL(xfrm4_prepare_output); static int xfrm4_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER - if (!skb->dst->xfrm) { + if (!skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(skb); } @@ -87,6 +87,6 @@ static int xfrm4_output_finish(struct sk_buff *skb) int xfrm4_output(struct sk_buff *skb) { return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, - NULL, skb->dst->dev, xfrm4_output_finish, + NULL, skb_dst(skb)->dev, xfrm4_output_finish, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 1c7f400a3cf..4aae658e550 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -277,7 +277,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - IP6_INC_STATS_BH(dev_net(skb->dst->dev), ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; @@ -288,7 +288,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) dstbuf = opt->dst1; #endif - dst = dst_clone(skb->dst); + dst = dst_clone(skb_dst(skb)); if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { dst_release(dst); skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; @@ -333,7 +333,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; @@ -343,7 +343,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) || skb->pkt_type != PACKET_HOST) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -358,7 +358,7 @@ looped_back: * processed by own */ if (!addr) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -384,7 +384,7 @@ looped_back: goto unknown_rh; /* Silently discard invalid RTH type 2 */ if (hdr->hdrlen != 2 || hdr->segments_left != 1) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; @@ -403,7 +403,7 @@ looped_back: n = hdr->hdrlen >> 1; if (hdr->segments_left > n) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - @@ -417,7 +417,7 @@ looped_back: if (skb_cloned(skb)) { /* the copy is a forwarded packet */ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -1; @@ -440,13 +440,13 @@ looped_back: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, IPPROTO_ROUTING) < 0) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } - if (!ipv6_chk_home_addr(dev_net(skb->dst->dev), addr)) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + if (!ipv6_chk_home_addr(dev_net(skb_dst(skb)->dev), addr)) { + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -458,7 +458,7 @@ looped_back: } if (ipv6_addr_is_multicast(addr)) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -468,17 +468,17 @@ looped_back: ipv6_addr_copy(addr, &ipv6_hdr(skb)->daddr); ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &daddr); - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); ip6_route_input(skb); - if (skb->dst->error) { + if (skb_dst(skb)->error) { skb_push(skb, skb->data - skb_network_header(skb)); dst_input(skb); return -1; } - if (skb->dst->dev->flags&IFF_LOOPBACK) { + if (skb_dst(skb)->dev->flags&IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0, skb->dev); @@ -494,7 +494,7 @@ looped_back: return -1; unknown_rh: - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb_network_header(skb)); return -1; @@ -552,11 +552,11 @@ void ipv6_exthdrs_exit(void) **********************************/ /* - * Note: we cannot rely on skb->dst before we assign it in ip6_route_input(). + * Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input(). */ static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb) { - return skb->dst ? ip6_dst_idev(skb->dst) : __in6_dev_get(skb->dev); + return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) : __in6_dev_get(skb->dev); } /* Router Alert as of RFC 2711 */ @@ -581,7 +581,7 @@ static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); u32 pkt_len; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 3c3732d50c1..cc4797dd832 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -228,7 +228,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) __inet6_csk_dst_store(sk, dst, NULL, NULL); } - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); /* Restore final destination back after routing done */ ipv6_addr_copy(&fl.fl6_dst, &np->daddr); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index bc1a920c34a..c3a07d75b5f 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -48,7 +48,7 @@ inline int ip6_rcv_finish( struct sk_buff *skb) { - if (skb->dst == NULL) + if (skb_dst(skb) == NULL) ip6_route_input(skb); return dst_input(skb); @@ -91,7 +91,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt * arrived via the sending interface (ethX), because of the * nature of scoping architecture. --yoshfuji */ - IP6CB(skb)->iif = skb->dst ? ip6_dst_idev(skb->dst)->dev->ifindex : dev->ifindex; + IP6CB(skb)->iif = skb_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; if (unlikely(!pskb_may_pull(skb, sizeof(*hdr)))) goto err; @@ -161,7 +161,7 @@ static int ip6_input_finish(struct sk_buff *skb) int nexthdr, raw; u8 hash; struct inet6_dev *idev; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); /* * Parse extension headers @@ -169,7 +169,7 @@ static int ip6_input_finish(struct sk_buff *skb) rcu_read_lock(); resubmit: - idev = ip6_dst_idev(skb->dst); + idev = ip6_dst_idev(skb_dst(skb)); if (!pskb_pull(skb, skb_transport_offset(skb))) goto discard; nhoff = IP6CB(skb)->nhoff; @@ -242,8 +242,8 @@ int ip6_mc_input(struct sk_buff *skb) struct ipv6hdr *hdr; int deliver; - IP6_UPD_PO_STATS_BH(dev_net(skb->dst->dev), - ip6_dst_idev(skb->dst), IPSTATS_MIB_INMCAST, + IP6_UPD_PO_STATS_BH(dev_net(skb_dst(skb)->dev), + ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INMCAST, skb->len); hdr = ipv6_hdr(skb); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 735a2bf4b5f..c8dc8e5a822 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -78,7 +78,7 @@ int __ip6_local_out(struct sk_buff *skb) len = 0; ipv6_hdr(skb)->payload_len = htons(len); - return nf_hook(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dst->dev, + return nf_hook(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev, dst_output); } @@ -96,7 +96,7 @@ EXPORT_SYMBOL_GPL(ip6_local_out); static int ip6_output_finish(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); if (dst->hh) return neigh_hh_output(dst->hh, skb); @@ -117,7 +117,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb) __skb_pull(newskb, skb_network_offset(newskb)); newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!newskb->dst); + WARN_ON(!skb_dst(newskb)); netif_rx(newskb); return 0; @@ -126,7 +126,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb) static int ip6_output2(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); @@ -134,7 +134,7 @@ static int ip6_output2(struct sk_buff *skb) if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL; - struct inet6_dev *idev = ip6_dst_idev(skb->dst); + struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && ((mroute6_socket(dev_net(dev)) && @@ -172,21 +172,21 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb) struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ? - skb->dst->dev->mtu : dst_mtu(skb->dst); + skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); } int ip6_output(struct sk_buff *skb) { - struct inet6_dev *idev = ip6_dst_idev(skb->dst); + struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (unlikely(idev->cnf.disable_ipv6)) { - IP6_INC_STATS(dev_net(skb->dst->dev), idev, + IP6_INC_STATS(dev_net(skb_dst(skb)->dev), idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || - dst_allfrag(skb->dst)) + dst_allfrag(skb_dst(skb))) return ip6_fragment(skb, ip6_output2); else return ip6_output2(skb); @@ -202,7 +202,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl->fl6_dst; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr; u8 proto = fl->proto; int seg_len = skb->len; @@ -222,7 +222,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, if (skb_headroom(skb) < head_room) { struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); if (skb2 == NULL) { - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -ENOBUFS; @@ -276,7 +276,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) { - IP6_UPD_PO_STATS(net, ip6_dst_idev(skb->dst), + IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUT, skb->len); return NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, dst_output); @@ -286,7 +286,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n"); skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } @@ -416,7 +416,7 @@ static inline int ip6_forward_finish(struct sk_buff *skb) int ip6_forward(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); @@ -485,7 +485,7 @@ int ip6_forward(struct sk_buff *skb) IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } - dst = skb->dst; + dst = skb_dst(skb); /* IPv6 specs say nothing about it, but it is clear that we cannot send redirects to source routed frames. @@ -566,8 +566,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; - dst_release(to->dst); - to->dst = dst_clone(from->dst); + skb_dst_drop(to); + skb_dst_set(to, dst_clone(skb_dst(from))); to->dev = from->dev; to->mark = from->mark; @@ -624,7 +624,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; - struct rt6_info *rt = (struct rt6_info*)skb->dst; + struct rt6_info *rt = (struct rt6_info*)skb_dst(skb); struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; @@ -632,7 +632,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; @@ -644,9 +644,9 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) * check should be redundant, but it's free.) */ if (!skb->local_df) { - skb->dev = skb->dst->dev; + skb->dev = skb_dst(skb)->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; @@ -696,7 +696,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) *prevhdr = NEXTHDR_FRAGMENT; tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!tmp_hdr) { - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); return -ENOMEM; } @@ -809,7 +809,7 @@ slow_path: if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; @@ -873,16 +873,16 @@ slow_path: if (err) goto fail; - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGCREATES); } - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGOKS); kfree_skb(skb); return err; fail: - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return err; @@ -1516,10 +1516,10 @@ int ip6_push_pending_frames(struct sock *sk) skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { - struct inet6_dev *idev = ip6_dst_idev(skb->dst); + struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type); ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); @@ -1545,8 +1545,8 @@ void ip6_flush_pending_frames(struct sock *sk) struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) { - if (skb->dst) - IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb->dst), + if (skb_dst(skb)) + IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index af256d47fd3..404d16a97d5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -532,8 +532,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!skb2) return 0; - dst_release(skb2->dst); - skb2->dst = NULL; + skb_dst_drop(skb2); + skb_pull(skb2, offset); skb_reset_network_header(skb2); eiph = ip_hdr(skb2); @@ -560,21 +560,21 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ip_rt_put(rt); goto out; } - skb2->dst = (struct dst_entry *)rt; + skb_dst_set(skb2, (struct dst_entry *)rt); } else { ip_rt_put(rt); if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || - skb2->dst->dev->type != ARPHRD_TUNNEL) + skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) goto out; } /* change mtu on this route */ if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) { - if (rel_info > dst_mtu(skb2->dst)) + if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb2->dst->ops->update_pmtu(skb2->dst, rel_info); + skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info); } icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -606,8 +606,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!skb2) return 0; - dst_release(skb2->dst); - skb2->dst = NULL; + skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); @@ -720,8 +719,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, skb->pkt_type = PACKET_HOST; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); skb->dev = t->dev; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); nf_reset(skb); dscp_ecn_decapsulate(t, ipv6h, skb); @@ -885,8 +883,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, } if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (skb->len > mtu) { *pmtu = mtu; err = -EMSGSIZE; @@ -910,8 +908,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, kfree_skb(skb); skb = new_skb; } - dst_release(skb->dst); - skb->dst = dst_clone(dst); + skb_dst_drop(skb); + skb_dst_set(skb, dst_clone(dst)); skb->transport_header = skb->network_header; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 228be551e9c..a35d8fc55b0 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -398,10 +398,9 @@ static int pim6_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; - dst_release(skb->dst); + skb_dst_drop(skb); reg_dev->stats.rx_bytes += skb->len; reg_dev->stats.rx_packets++; - skb->dst = NULL; nf_reset(skb); netif_rx(skb); dev_put(reg_dev); @@ -849,7 +848,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); - skb->dst = dst_clone(pkt->dst); + skb_dst_set(skb, dst_clone(skb_dst(pkt))); skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -1487,7 +1486,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) static inline int ip6mr_forward2_finish(struct sk_buff *skb) { - IP6_INC_STATS_BH(dev_net(skb->dst->dev), ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); return dst_output(skb); } @@ -1532,8 +1531,8 @@ static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) if (!dst) goto out_free; - dst_release(skb->dst); - skb->dst = dst; + skb_dst_drop(skb); + skb_dst_set(skb, dst); /* * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally @@ -1722,7 +1721,7 @@ int ip6mr_get_route(struct net *net, { int err; struct mfc6_cache *cache; - struct rt6_info *rt = (struct rt6_info *)skb->dst; + struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); read_lock(&mrt_lock); cache = ip6mr_cache_find(net, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 4b48819a5b8..4b264ed40a8 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1448,6 +1448,7 @@ static void mld_sendpack(struct sk_buff *skb) struct net *net = dev_net(skb->dev); int err; struct flowi fl; + struct dst_entry *dst; IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); @@ -1459,9 +1460,9 @@ static void mld_sendpack(struct sk_buff *skb) IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb), mldlen, 0)); - skb->dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); + dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); - if (!skb->dst) { + if (!dst) { err = -ENOMEM; goto err_out; } @@ -1470,7 +1471,8 @@ static void mld_sendpack(struct sk_buff *skb) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(net, &skb->dst, &fl, NULL, 0); + err = xfrm_lookup(net, &dst, &fl, NULL, 0); + skb_dst_set(skb, dst); if (err) goto err_out; @@ -1775,6 +1777,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct flowi fl; + struct dst_entry *dst; if (type == ICMPV6_MGM_REDUCTION) snd_addr = &in6addr_linklocal_allrouters; @@ -1828,8 +1831,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) idev = in6_dev_get(skb->dev); - skb->dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); - if (!skb->dst) { + dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); + if (!dst) { err = -ENOMEM; goto err_out; } @@ -1838,11 +1841,11 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(net, &skb->dst, &fl, NULL, 0); + err = xfrm_lookup(net, &dst, &fl, NULL, 0); if (err) goto err_out; - + skb_dst_set(skb, dst); err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, dst_output); out: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 1d13d996498..9eb68e92cc1 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -530,7 +530,7 @@ void ndisc_send_skb(struct sk_buff *skb, return; } - skb->dst = dst; + skb_dst_set(skb, dst); idev = in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); @@ -1612,7 +1612,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, len, IPPROTO_ICMPV6, csum_partial(icmph, len, 0)); - buff->dst = dst; + skb_dst_set(buff, dst); idev = in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev, diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 834cea69fb5..d5ed92b1434 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -12,7 +12,7 @@ int ip6_route_me_harder(struct sk_buff *skb) { - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); struct ipv6hdr *iph = ipv6_hdr(skb); struct dst_entry *dst; struct flowi fl = { @@ -28,9 +28,15 @@ int ip6_route_me_harder(struct sk_buff *skb) #ifdef CONFIG_XFRM if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - xfrm_decode_session(skb, &fl, AF_INET6) == 0) - if (xfrm_lookup(net, &skb->dst, &fl, skb->sk, 0)) + xfrm_decode_session(skb, &fl, AF_INET6) == 0) { + struct dst_entry *dst2 = skb_dst(skb); + + if (xfrm_lookup(net, &dst2, &fl, skb->sk, 0)) { + skb_dst_set(skb, NULL); return -1; + } + skb_dst_set(skb, dst2); + } #endif if (dst->error) { @@ -41,9 +47,9 @@ int ip6_route_me_harder(struct sk_buff *skb) } /* Drop old route. */ - dst_release(skb->dst); + skb_dst_drop(skb); - skb->dst = dst; + skb_dst_set(skb, dst); return 0; } EXPORT_SYMBOL(ip6_route_me_harder); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 5a2d0a41694..5a7f00cd15c 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -112,7 +112,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) return; } - nskb->dst = dst; + skb_dst_set(nskb, dst); skb_reserve(nskb, hh_len + dst->header_len); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e99307fba0b..36a090d87a3 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -625,7 +625,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); skb_put(skb, length); skb_reset_network_header(skb); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index e9ac7a12f59..54a387d31e1 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -267,7 +267,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev, *next; struct net_device *dev; int offset, end; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); if (fq->q.last_in & INET_FRAG_COMPLETE) goto err; @@ -277,7 +277,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((u8 *)&fhdr->frag_off - @@ -310,7 +310,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, /* RFC2460 says always send parameter problem in * this case. -DaveM */ - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, payload_len)); @@ -434,7 +434,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, return -1; err: - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; @@ -576,9 +576,9 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_hdr *fhdr; struct frag_queue *fq; struct ipv6hdr *hdr = ipv6_hdr(skb); - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMREQDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); /* Jumbo payload inhibits frag. header */ if (hdr->payload_len==0) @@ -595,17 +595,17 @@ static int ipv6_frag_rcv(struct sk_buff *skb) /* It is not a fragmented frame */ skb->transport_header += sizeof(struct frag_hdr); IP6_INC_STATS_BH(net, - ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMOKS); + ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS); IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); return 1; } if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh) - ip6_evictor(net, ip6_dst_idev(skb->dst)); + ip6_evictor(net, ip6_dst_idev(skb_dst(skb))); if ((fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, - ip6_dst_idev(skb->dst))) != NULL) { + ip6_dst_idev(skb_dst(skb)))) != NULL) { int ret; spin_lock(&fq->q.lock); @@ -617,12 +617,12 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return ret; } - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; fail_hdr: - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb)); return -1; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 032a5ec391c..658293ea05b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -800,7 +800,7 @@ void ip6_route_input(struct sk_buff *skb) if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; - skb->dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input); + skb_dst_set(skb, fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input)); } static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, @@ -911,7 +911,7 @@ static void ip6_link_failure(struct sk_buff *skb) icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev); - rt = (struct rt6_info *) skb->dst; + rt = (struct rt6_info *) skb_dst(skb); if (rt) { if (rt->rt6i_flags&RTF_CACHE) { dst_set_expires(&rt->u.dst, 0); @@ -1868,7 +1868,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) static int ip6_pkt_drop(struct sk_buff *skb, int code, int ipstats_mib_noroutes) { int type; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); switch (ipstats_mib_noroutes) { case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); @@ -1895,7 +1895,7 @@ static int ip6_pkt_discard(struct sk_buff *skb) static int ip6_pkt_discard_out(struct sk_buff *skb) { - skb->dev = skb->dst->dev; + skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } @@ -1908,7 +1908,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb) static int ip6_pkt_prohibit_out(struct sk_buff *skb) { - skb->dev = skb->dst->dev; + skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } @@ -2366,7 +2366,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl); - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b3a59bd40f0..68e52308e55 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -575,8 +575,7 @@ static int ipip6_rcv(struct sk_buff *skb) tunnel->dev->stats.rx_packets++; tunnel->dev->stats.rx_bytes += skb->len; skb->dev = tunnel->dev; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); nf_reset(skb); ipip6_ecn_decapsulate(iph, skb); netif_rx(skb); @@ -638,8 +637,8 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (dev->priv_flags & IFF_ISATAP) { struct neighbour *neigh = NULL; - if (skb->dst) - neigh = skb->dst->neighbour; + if (skb_dst(skb)) + neigh = skb_dst(skb)->neighbour; if (neigh == NULL) { if (net_ratelimit()) @@ -663,8 +662,8 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (!dst) { struct neighbour *neigh = NULL; - if (skb->dst) - neigh = skb->dst->neighbour; + if (skb_dst(skb)) + neigh = skb_dst(skb)->neighbour; if (neigh == NULL) { if (net_ratelimit()) @@ -714,7 +713,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (tiph->frag_off) mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); else - mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu; + mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (mtu < 68) { stats->collisions++; @@ -723,8 +722,8 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (tunnel->parms.iph.daddr && skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (tunnel->parms.iph.daddr && skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (skb->len > mtu) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); @@ -768,8 +767,8 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags = 0; - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ea37741062a..53b6a4192b1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -981,9 +981,10 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, struct tcphdr *th = tcp_hdr(skb), *t1; struct sk_buff *buff; struct flowi fl; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); + struct dst_entry *dst; __be32 *topt; if (ts) @@ -1052,8 +1053,9 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, * Underlying function will use this to retrieve the network * namespace */ - if (!ip6_dst_lookup(ctl_sk, &buff->dst, &fl)) { - if (xfrm_lookup(net, &buff->dst, &fl, NULL, 0) >= 0) { + if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) { + if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { + skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl, NULL, 0); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); if (rst) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8905712cfbb..fc333d85472 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -177,10 +177,9 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, if (unlikely(sk = skb_steal_sock(skb))) return sk; - else - return __udp6_lib_lookup(dev_net(skb->dst->dev), &iph->saddr, sport, - &iph->daddr, dport, inet6_iif(skb), - udptable); + return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport, + &iph->daddr, dport, inet6_iif(skb), + udptable); } /* diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index e20529b4c82..3927832227b 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -31,7 +31,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) */ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *top_iph; int dsfield; @@ -45,7 +45,7 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl, sizeof(top_iph->flow_lbl)); - top_iph->nexthdr = xfrm_af2proto(skb->dst->ops->family); + top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family); dsfield = XFRM_MODE_SKB_CB(skb)->tos; dsfield = INET_ECN_encapsulate(dsfield, dsfield); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 5ee5a031bc9..c4f4eef032a 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -30,7 +30,7 @@ EXPORT_SYMBOL(xfrm6_find_1stfragopt); static int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); mtu = dst_mtu(dst); if (mtu < IPV6_MIN_MTU) @@ -90,6 +90,6 @@ static int xfrm6_output_finish(struct sk_buff *skb) int xfrm6_output(struct sk_buff *skb) { - return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb->dst->dev, + return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb_dst(skb)->dev, xfrm6_output_finish); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 425ab144f15..5874657af7f 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -260,8 +260,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ip_send_check(ip_hdr(skb)); /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -324,8 +324,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -388,8 +388,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) @@ -465,8 +465,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) @@ -553,8 +553,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_RL("ip_vs_tunnel_xmit(): mtu less than 68\n"); goto tx_error; } - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); df |= (old_iph->frag_off & htons(IP_DF)); @@ -596,8 +596,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. @@ -665,8 +665,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_RL("ip_vs_tunnel_xmit_v6(): mtu less than 1280\n"); goto tx_error; } - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); @@ -702,8 +702,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. @@ -775,8 +775,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ip_send_check(ip_hdr(skb)); /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -828,8 +828,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -900,8 +900,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* drop the old route when skb is not shared */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); ip_vs_nat_icmp(skb, pp, cp, 0); @@ -975,8 +975,8 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* drop the old route when skb is not shared */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); ip_vs_nat_icmp_v6(skb, pp, cp, 0); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 117b80112fc..a6d6ec320fb 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -176,7 +176,7 @@ static bool gre_invert_tuple(struct nf_conntrack_tuple *tuple, static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) { - struct net *net = dev_net(skb->dev ? skb->dev : skb->dst->dev); + struct net *net = dev_net(skb->dev ? skb->dev : skb_dst(skb)->dev); const struct gre_hdr_pptp *pgrehdr; struct gre_hdr_pptp _pgrehdr; __be16 srckey; diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 4f3b1f80879..eda64c1cb1e 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -73,11 +73,11 @@ tcpmss_mangle_packet(struct sk_buff *skb, } if (info->mss == XT_TCPMSS_CLAMP_PMTU) { - if (dst_mtu(skb->dst) <= minlen) { + if (dst_mtu(skb_dst(skb)) <= minlen) { if (net_ratelimit()) printk(KERN_ERR "xt_TCPMSS: " "unknown or invalid path-MTU (%u)\n", - dst_mtu(skb->dst)); + dst_mtu(skb_dst(skb))); return -1; } if (in_mtu <= minlen) { @@ -86,7 +86,7 @@ tcpmss_mangle_packet(struct sk_buff *skb, "invalid path-MTU (%u)\n", in_mtu); return -1; } - newmss = min(dst_mtu(skb->dst), in_mtu) - minlen; + newmss = min(dst_mtu(skb_dst(skb)), in_mtu) - minlen; } else newmss = info->mss; diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c index 328bd20ddd2..4cbfebda8fa 100644 --- a/net/netfilter/xt_policy.c +++ b/net/netfilter/xt_policy.c @@ -86,7 +86,7 @@ match_policy_out(const struct sk_buff *skb, const struct xt_policy_info *info, unsigned short family) { const struct xt_policy_elem *e; - const struct dst_entry *dst = skb->dst; + const struct dst_entry *dst = skb_dst(skb); int strict = info->flags & XT_POLICY_MATCH_STRICT; int i, pos; diff --git a/net/netfilter/xt_realm.c b/net/netfilter/xt_realm.c index 67419287bc7..484d1689bfd 100644 --- a/net/netfilter/xt_realm.c +++ b/net/netfilter/xt_realm.c @@ -25,7 +25,7 @@ static bool realm_mt(const struct sk_buff *skb, const struct xt_match_param *par) { const struct xt_realm_info *info = par->matchinfo; - const struct dst_entry *dst = skb->dst; + const struct dst_entry *dst = skb_dst(skb); return (info->id == (dst->tclassid & info->mask)) ^ info->invert; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6da9f38ef5c..4f76e5552d8 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -372,8 +372,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct goto oom; /* drop any routing info */ - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); /* drop conntrack reference */ nf_reset(skb); @@ -621,8 +620,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet skb_set_owner_r(skb, sk); skb->dev = NULL; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); /* drop conntrack reference */ nf_reset(skb); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 0ef4e3065bc..9402a7fd378 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -84,7 +84,7 @@ static u32 flow_get_dst(const struct sk_buff *skb) case htons(ETH_P_IPV6): return ntohl(ipv6_hdr(skb)->daddr.s6_addr32[3]); default: - return addr_fold(skb->dst) ^ (__force u16)skb->protocol; + return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol; } } @@ -163,7 +163,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb) break; } default: - res = addr_fold(skb->dst) ^ (__force u16)skb->protocol; + res = addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol; } return res; @@ -251,8 +251,8 @@ fallback: static u32 flow_get_rtclassid(const struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ROUTE - if (skb->dst) - return skb->dst->tclassid; + if (skb_dst(skb)) + return skb_dst(skb)->tclassid; #endif return 0; } diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index bdf1f4172ee..dd872d5383e 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -137,7 +137,7 @@ static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp, u32 id, h; int iif, dont_cache = 0; - if ((dst = skb->dst) == NULL) + if ((dst = skb_dst(skb)) == NULL) goto failure; id = dst->tclassid; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index b6b588bed4e..266151ae85a 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -246,11 +246,11 @@ META_COLLECTOR(int_tcindex) META_COLLECTOR(int_rtclassid) { - if (unlikely(skb->dst == NULL)) + if (unlikely(skb_dst(skb) == NULL)) *err = -1; else #ifdef CONFIG_NET_CLS_ROUTE - dst->value = skb->dst->tclassid; + dst->value = skb_dst(skb)->tclassid; #else dst->value = 0; #endif diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 33133d27b53..8706920a6d4 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -149,7 +149,7 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) break; } default: - h = (unsigned long)skb->dst ^ skb->protocol; + h = (unsigned long)skb_dst(skb) ^ skb->protocol; h2 = (unsigned long)skb->sk; } diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index a886496bdc3..cb1cb1e76b9 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -222,7 +222,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device * { struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0); struct teql_sched_data *q = qdisc_priv(dev_queue->qdisc); - struct neighbour *mn = skb->dst->neighbour; + struct neighbour *mn = skb_dst(skb)->neighbour; struct neighbour *n = q->ncache; if (mn->tbl == NULL) @@ -262,8 +262,8 @@ static inline int teql_resolve(struct sk_buff *skb, return -ENODEV; if (dev->header_ops == NULL || - skb->dst == NULL || - skb->dst->neighbour == NULL) + skb_dst(skb) == NULL || + skb_dst(skb)->neighbour == NULL) return 0; return __teql_resolve(skb, skb_res, dev); } diff --git a/net/sctp/output.c b/net/sctp/output.c index f0c91df59d4..b7641144451 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -405,10 +405,10 @@ int sctp_packet_transmit(struct sctp_packet *packet) sctp_assoc_sync_pmtu(asoc); } } - nskb->dst = dst_clone(tp->dst); - if (!nskb->dst) + dst = dst_clone(tp->dst); + skb_dst_set(nskb, dst); + if (dst) goto no_route; - dst = nskb->dst; /* Build the SCTP header. */ sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr)); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index e1859614601..6c2d6158655 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -918,7 +918,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) UDPX_INC_STATS_BH(sk, UDP_MIB_INDATAGRAMS); /* Something worked... */ - dst_confirm(skb->dst); + dst_confirm(skb_dst(skb)); xprt_adjust_cwnd(task, copied); xprt_update_rtt(task); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index b4a13178fb4..e0009c17d80 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -251,8 +251,7 @@ resume: nf_reset(skb); if (decaps) { - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); netif_rx(skb); return 0; } else { diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index c235597ba8d..b9fe13138c0 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -22,7 +22,7 @@ static int xfrm_output2(struct sk_buff *skb); static int xfrm_state_check_space(struct xfrm_state *x, struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); int nhead = dst->header_len + LL_RESERVED_SPACE(dst->dev) - skb_headroom(skb); int ntail = dst->dev->needed_tailroom - skb_tailroom(skb); @@ -39,7 +39,7 @@ static int xfrm_state_check_space(struct xfrm_state *x, struct sk_buff *skb) static int xfrm_output_one(struct sk_buff *skb, int err) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; struct net *net = xs_net(x); @@ -94,12 +94,13 @@ resume: goto error_nolock; } - if (!(skb->dst = dst_pop(dst))) { + dst = dst_pop(dst); + if (!dst) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); err = -EHOSTUNREACH; goto error_nolock; } - dst = skb->dst; + skb_dst_set(skb, dst); x = dst->xfrm; } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)); @@ -119,16 +120,16 @@ int xfrm_output_resume(struct sk_buff *skb, int err) while (likely((err = xfrm_output_one(skb, err)) == 0)) { nf_reset(skb); - err = skb->dst->ops->local_out(skb); + err = skb_dst(skb)->ops->local_out(skb); if (unlikely(err != 1)) goto out; - if (!skb->dst->xfrm) + if (!skb_dst(skb)->xfrm) return dst_output(skb); - err = nf_hook(skb->dst->ops->family, + err = nf_hook(skb_dst(skb)->ops->family, NF_INET_POST_ROUTING, skb, - NULL, skb->dst->dev, xfrm_output2); + NULL, skb_dst(skb)->dev, xfrm_output2); if (unlikely(err != 1)) goto out; } @@ -179,7 +180,7 @@ static int xfrm_output_gso(struct sk_buff *skb) int xfrm_output(struct sk_buff *skb) { - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); int err; if (skb_is_gso(skb)) @@ -202,7 +203,7 @@ int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_mode *inner_mode; if (x->sel.family == AF_UNSPEC) inner_mode = xfrm_ip2inner_mode(x, - xfrm_af2proto(skb->dst->ops->family)); + xfrm_af2proto(skb_dst(skb)->ops->family)); else inner_mode = x->inner_mode; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9c068ab3a83..cb81ca35b0d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2027,6 +2027,8 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct flowi fl; + struct dst_entry *dst; + int res; if (xfrm_decode_session(skb, &fl, family) < 0) { /* XXX: we should have something like FWDHDRERROR here. */ @@ -2034,7 +2036,11 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) return 0; } - return xfrm_lookup(net, &skb->dst, &fl, NULL, 0) == 0; + dst = skb_dst(skb); + + res = xfrm_lookup(net, &dst, &fl, NULL, 0) == 0; + skb_dst_set(skb, dst); + return res; } EXPORT_SYMBOL(__xfrm_route_forward); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 2fcad7c33ea..4bfc6153ad4 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4503,7 +4503,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex, * when the packet is on it's final way out. * NOTE: there appear to be some IPv6 multicast cases where skb->dst * is NULL, in this case go ahead and apply access control. */ - if (skb->dst != NULL && skb->dst->xfrm != NULL) + if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL) return NF_ACCEPT; #endif secmark_active = selinux_secmark_enabled(); diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c index c0eb72013d6..72b18452e1a 100644 --- a/security/selinux/xfrm.c +++ b/security/selinux/xfrm.c @@ -447,7 +447,7 @@ int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb, struct dst_entry *dst; int rc = 0; - dst = skb->dst; + dst = skb_dst(skb); if (dst) { struct dst_entry *dst_test; -- cgit v1.2.3-70-g09d2 From e5b9215ef9a274eb9fb65f6aa4602ad82d10a6cb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 2 Jun 2009 05:20:21 +0000 Subject: net: skb cleanup Can remove anonymous union now it has one field. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9ef6eb20247..7305da92be8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -322,9 +322,7 @@ struct sk_buff { ktime_t tstamp; struct net_device *dev; - union { - unsigned long _skb_dst; - }; + unsigned long _skb_dst; #ifdef CONFIG_XFRM struct sec_path *sp; #endif -- cgit v1.2.3-70-g09d2 From eae3f29cc73f83cc3f1891d3ad40021b5172c630 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 5 Jun 2009 04:03:35 +0000 Subject: net: num_dma_maps is not used Get rid of num_dma_maps in struct skb_shared_info, as it seems unused. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 --- net/core/skb_dma_map.c | 1 - 2 files changed, 4 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7305da92be8..7485058125e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -194,9 +194,6 @@ struct skb_shared_info { unsigned short gso_type; __be32 ip6_frag_id; union skb_shared_tx tx_flags; -#ifdef CONFIG_HAS_DMA - unsigned int num_dma_maps; -#endif struct sk_buff *frag_list; struct skb_shared_hwtstamps hwtstamps; skb_frag_t frags[MAX_SKB_FRAGS]; diff --git a/net/core/skb_dma_map.c b/net/core/skb_dma_map.c index 86234923a3b..7adb623ef66 100644 --- a/net/core/skb_dma_map.c +++ b/net/core/skb_dma_map.c @@ -30,7 +30,6 @@ int skb_dma_map(struct device *dev, struct sk_buff *skb, goto unwind; sp->dma_maps[i + 1] = map; } - sp->num_dma_maps = i + 1; return 0; -- cgit v1.2.3-70-g09d2 From 042a53a9e437feaf2230dd2cadcecfae9c7bfe05 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 5 Jun 2009 04:04:16 +0000 Subject: net: skb_shared_info optimization skb_dma_unmap() is quite expensive for small packets, because we use two different cache lines from skb_shared_info. One to access nr_frags, one to access dma_maps[0] Instead of dma_maps being an array of MAX_SKB_FRAGS + 1 elements, let dma_head alone in a new dma_head field, close to nr_frags, to reduce cache lines misses. Tested on my dev machine (bnx2 & tg3 adapters), nice speedup ! Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/bnx2.c | 6 +++--- drivers/net/e1000/e1000_main.c | 4 ++-- drivers/net/e1000e/netdev.c | 4 ++-- drivers/net/igb/igb_main.c | 5 ++--- drivers/net/igbvf/netdev.c | 5 ++--- drivers/net/ixgb/ixgb_main.c | 4 ++-- drivers/net/ixgbe/ixgbe_main.c | 4 ++-- drivers/net/tg3.c | 10 +++++----- include/linux/skbuff.h | 5 ++++- net/core/skb_dma_map.c | 12 ++++++------ 10 files changed, 30 insertions(+), 29 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index f53017250e0..391d2d47089 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -5487,7 +5487,7 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode) dev_kfree_skb(skb); return -EIO; } - map = skb_shinfo(skb)->dma_maps[0]; + map = skb_shinfo(skb)->dma_head; REG_WR(bp, BNX2_HC_COMMAND, bp->hc_cmd | BNX2_HC_COMMAND_COAL_NOW_WO_INT); @@ -6167,7 +6167,7 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) } sp = skb_shinfo(skb); - mapping = sp->dma_maps[0]; + mapping = sp->dma_head; tx_buf = &txr->tx_buf_ring[ring_prod]; tx_buf->skb = skb; @@ -6191,7 +6191,7 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) txbd = &txr->tx_desc_ring[ring_prod]; len = frag->size; - mapping = sp->dma_maps[i + 1]; + mapping = sp->dma_maps[i]; txbd->tx_bd_haddr_hi = (u64) mapping >> 32; txbd->tx_bd_haddr_lo = (u64) mapping & 0xffffffff; diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index 05e87a59f1c..8d36743c814 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -2998,7 +2998,7 @@ static int e1000_tx_map(struct e1000_adapter *adapter, size -= 4; buffer_info->length = size; - buffer_info->dma = map[0] + offset; + buffer_info->dma = skb_shinfo(skb)->dma_head + offset; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; @@ -3039,7 +3039,7 @@ static int e1000_tx_map(struct e1000_adapter *adapter, size -= 4; buffer_info->length = size; - buffer_info->dma = map[f + 1] + offset; + buffer_info->dma = map[f] + offset; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 38694c79edc..9043f1b845f 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -3916,7 +3916,7 @@ static int e1000_tx_map(struct e1000_adapter *adapter, buffer_info->length = size; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = map[0] + offset; + buffer_info->dma = skb_shinfo(skb)->dma_head + offset; count++; len -= size; @@ -3947,7 +3947,7 @@ static int e1000_tx_map(struct e1000_adapter *adapter, buffer_info->length = size; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = map[f + 1] + offset; + buffer_info->dma = map[f] + offset; len -= size; offset += size; diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index 958b2879da4..ea17319624a 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -3139,8 +3139,7 @@ static inline int igb_tx_map_adv(struct igb_adapter *adapter, /* set time_stamp *before* dma to help avoid a possible race */ buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = map[count]; - count++; + buffer_info->dma = skb_shinfo(skb)->dma_head; for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { struct skb_frag_struct *frag; @@ -3164,7 +3163,7 @@ static inline int igb_tx_map_adv(struct igb_adapter *adapter, tx_ring->buffer_info[i].skb = skb; tx_ring->buffer_info[first].next_to_watch = i; - return count; + return count + 1; } static inline void igb_tx_queue_adv(struct igb_adapter *adapter, diff --git a/drivers/net/igbvf/netdev.c b/drivers/net/igbvf/netdev.c index 5f7ba1a4990..22aadb7884f 100644 --- a/drivers/net/igbvf/netdev.c +++ b/drivers/net/igbvf/netdev.c @@ -2119,8 +2119,7 @@ static inline int igbvf_tx_map_adv(struct igbvf_adapter *adapter, /* set time_stamp *before* dma to help avoid a possible race */ buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = map[count]; - count++; + buffer_info->dma = skb_shinfo(skb)->dma_head; for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { struct skb_frag_struct *frag; @@ -2144,7 +2143,7 @@ static inline int igbvf_tx_map_adv(struct igbvf_adapter *adapter, tx_ring->buffer_info[i].skb = skb; tx_ring->buffer_info[first].next_to_watch = i; - return count; + return count + 1; } static inline void igbvf_tx_queue_adv(struct igbvf_adapter *adapter, diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c index 6eb7f37a113..9c897cf86b9 100644 --- a/drivers/net/ixgb/ixgb_main.c +++ b/drivers/net/ixgb/ixgb_main.c @@ -1300,7 +1300,7 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, buffer_info->length = size; WARN_ON(buffer_info->dma != 0); buffer_info->time_stamp = jiffies; - buffer_info->dma = map[0] + offset; + buffer_info->dma = skb_shinfo(skb)->dma_head + offset; pci_map_single(adapter->pdev, skb->data + offset, size, @@ -1340,7 +1340,7 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, buffer_info->length = size; buffer_info->time_stamp = jiffies; - buffer_info->dma = map[f + 1] + offset; + buffer_info->dma = map[f] + offset; buffer_info->next_to_watch = 0; len -= size; diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index d36003cbb6d..09994e920d5 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -4837,7 +4837,7 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter, size = min(len, (uint)IXGBE_MAX_DATA_PER_TXD); tx_buffer_info->length = size; - tx_buffer_info->dma = map[0] + offset; + tx_buffer_info->dma = skb_shinfo(skb)->dma_head + offset; tx_buffer_info->time_stamp = jiffies; tx_buffer_info->next_to_watch = i; @@ -4869,7 +4869,7 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter, size = min(len, (uint)IXGBE_MAX_DATA_PER_TXD); tx_buffer_info->length = size; - tx_buffer_info->dma = map[f + 1] + offset; + tx_buffer_info->dma = map[f] + offset; tx_buffer_info->time_stamp = jiffies; tx_buffer_info->next_to_watch = i; diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index a39b534fb43..46a3f86125b 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -5021,7 +5021,7 @@ static int tigon3_dma_hwbug_workaround(struct tg3 *tp, struct sk_buff *skb, /* New SKB is guaranteed to be linear. */ entry = *start; ret = skb_dma_map(&tp->pdev->dev, new_skb, DMA_TO_DEVICE); - new_addr = skb_shinfo(new_skb)->dma_maps[0]; + new_addr = skb_shinfo(new_skb)->dma_head; /* Make sure new skb does not cross any 4G boundaries. * Drop the packet if it does. @@ -5155,7 +5155,7 @@ static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) sp = skb_shinfo(skb); - mapping = sp->dma_maps[0]; + mapping = sp->dma_head; tp->tx_buffers[entry].skb = skb; @@ -5173,7 +5173,7 @@ static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; len = frag->size; - mapping = sp->dma_maps[i + 1]; + mapping = sp->dma_maps[i]; tp->tx_buffers[entry].skb = NULL; tg3_set_txd(tp, entry, mapping, len, @@ -5331,7 +5331,7 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev) sp = skb_shinfo(skb); - mapping = sp->dma_maps[0]; + mapping = sp->dma_head; tp->tx_buffers[entry].skb = skb; @@ -5356,7 +5356,7 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev) skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; len = frag->size; - mapping = sp->dma_maps[i + 1]; + mapping = sp->dma_maps[i]; tp->tx_buffers[entry].skb = NULL; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7485058125e..aad484cd586 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -189,6 +189,9 @@ struct skb_shared_info { atomic_t dataref; unsigned short nr_frags; unsigned short gso_size; +#ifdef CONFIG_HAS_DMA + dma_addr_t dma_head; +#endif /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; unsigned short gso_type; @@ -198,7 +201,7 @@ struct skb_shared_info { struct skb_shared_hwtstamps hwtstamps; skb_frag_t frags[MAX_SKB_FRAGS]; #ifdef CONFIG_HAS_DMA - dma_addr_t dma_maps[MAX_SKB_FRAGS + 1]; + dma_addr_t dma_maps[MAX_SKB_FRAGS]; #endif /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ diff --git a/net/core/skb_dma_map.c b/net/core/skb_dma_map.c index 7adb623ef66..79687dfd695 100644 --- a/net/core/skb_dma_map.c +++ b/net/core/skb_dma_map.c @@ -20,7 +20,7 @@ int skb_dma_map(struct device *dev, struct sk_buff *skb, if (dma_mapping_error(dev, map)) goto out_err; - sp->dma_maps[0] = map; + sp->dma_head = map; for (i = 0; i < sp->nr_frags; i++) { skb_frag_t *fp = &sp->frags[i]; @@ -28,7 +28,7 @@ int skb_dma_map(struct device *dev, struct sk_buff *skb, fp->size, dir); if (dma_mapping_error(dev, map)) goto unwind; - sp->dma_maps[i + 1] = map; + sp->dma_maps[i] = map; } return 0; @@ -37,10 +37,10 @@ unwind: while (--i >= 0) { skb_frag_t *fp = &sp->frags[i]; - dma_unmap_page(dev, sp->dma_maps[i + 1], + dma_unmap_page(dev, sp->dma_maps[i], fp->size, dir); } - dma_unmap_single(dev, sp->dma_maps[0], + dma_unmap_single(dev, sp->dma_head, skb_headlen(skb), dir); out_err: return -ENOMEM; @@ -53,12 +53,12 @@ void skb_dma_unmap(struct device *dev, struct sk_buff *skb, struct skb_shared_info *sp = skb_shinfo(skb); int i; - dma_unmap_single(dev, sp->dma_maps[0], + dma_unmap_single(dev, sp->dma_head, skb_headlen(skb), dir); for (i = 0; i < sp->nr_frags; i++) { skb_frag_t *fp = &sp->frags[i]; - dma_unmap_page(dev, sp->dma_maps[i + 1], + dma_unmap_page(dev, sp->dma_maps[i], fp->size, dir); } } -- cgit v1.2.3-70-g09d2 From ee0398717078260ee4ffa97d407071bc774e2dac Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 9 Jun 2009 00:17:13 -0700 Subject: skbuff: Add frag list abstraction interfaces. With the hope that these can be used to eliminate direct references to the frag list implementation. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index aad484cd586..f1c93b878b3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1077,7 +1077,7 @@ extern void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size); #define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags) -#define SKB_FRAG_ASSERT(skb) BUG_ON(skb_shinfo(skb)->frag_list) +#define SKB_FRAG_ASSERT(skb) BUG_ON(skb_has_frags(skb)) #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET @@ -1716,6 +1716,25 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) skb = skb->prev) +static inline bool skb_has_frags(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->frag_list != NULL; +} + +static inline void skb_frag_list_init(struct sk_buff *skb) +{ + skb_shinfo(skb)->frag_list = NULL; +} + +static inline void skb_frag_add_head(struct sk_buff *skb, struct sk_buff *frag) +{ + frag->next = skb_shinfo(skb)->frag_list; + skb_shinfo(skb)->frag_list = frag; +} + +#define skb_walk_frags(skb, iter) \ + for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) + extern struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, int *peeked, int *err); extern struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, -- cgit v1.2.3-70-g09d2 From 8f77f3849cc3ae2d6df9301785a3d316ea7d7ee1 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 7 Jun 2009 21:58:37 +0200 Subject: mac80211: do not pass PS frames out of mac80211 again In order to handle powersave frames properly we had needed to pass these out to the device queues again, and introduce the skb->requeue bit. This, however, also has unnecessary overhead by needing to 'clean up' already tried frames, and this clean-up code is also buggy when software encryption is used. Instead of sending the frames via the master netdev queue again, simply put them into the pending queue. This also fixes a problem where frames for that particular station could be reordered when some were still on the software queues and older ones are re-injected into the software queue after them. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/skbuff.h | 4 --- include/net/mac80211.h | 3 +++ net/core/skbuff.c | 1 - net/mac80211/ieee80211_i.h | 5 ++++ net/mac80211/main.c | 61 +++++----------------------------------------- net/mac80211/rx.c | 25 +++++++------------ net/mac80211/tx.c | 3 ++- net/mac80211/util.c | 46 ++++++++++++++++++++++++++++++++++ net/mac80211/wme.c | 2 +- 9 files changed, 72 insertions(+), 78 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f1c93b878b3..fa51293f270 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -304,9 +304,6 @@ typedef unsigned char *sk_buff_data_t; * @tc_verd: traffic control verdict * @ndisc_nodetype: router type (from link layer) * @do_not_encrypt: set to prevent encryption of this frame - * @requeue: set to indicate that the wireless core should attempt - * a software retry on this frame if we failed to - * receive an ACK for it * @dma_cookie: a cookie to one of several possible DMA operations * done by skb DMA functions * @secmark: security marking @@ -380,7 +377,6 @@ struct sk_buff { #endif #if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE) __u8 do_not_encrypt:1; - __u8 requeue:1; #endif /* 0/13/14 bit hole */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 17d61d19d91..c0610447697 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -239,6 +239,8 @@ struct ieee80211_bss_conf { * @IEEE80211_TX_INTFL_NEED_TXPROCESSING: completely internal to mac80211, * used to indicate that a pending frame requires TX processing before * it can be sent out. + * @IEEE80211_TX_INTFL_RETRIED: completely internal to mac80211, + * used to indicate that a frame was already retried due to PS */ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_REQ_TX_STATUS = BIT(0), @@ -256,6 +258,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_RATE_CTRL_PROBE = BIT(12), IEEE80211_TX_INTFL_RCALGO = BIT(13), IEEE80211_TX_INTFL_NEED_TXPROCESSING = BIT(14), + IEEE80211_TX_INTFL_RETRIED = BIT(15), }; /** diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 49961ba3c0f..b94d777e3eb 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -552,7 +552,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->vlan_tci = old->vlan_tci; #if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE) new->do_not_encrypt = old->do_not_encrypt; - new->requeue = old->requeue; #endif skb_copy_secmark(new, old); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c088c46704a..4dbc2896419 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -589,6 +589,7 @@ enum queue_stop_reason { IEEE80211_QUEUE_STOP_REASON_AGGREGATION, IEEE80211_QUEUE_STOP_REASON_SUSPEND, IEEE80211_QUEUE_STOP_REASON_PENDING, + IEEE80211_QUEUE_STOP_REASON_SKB_ADD, }; struct ieee80211_master_priv { @@ -1121,6 +1122,10 @@ void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason); void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason); +void ieee80211_add_pending_skb(struct ieee80211_local *local, + struct sk_buff *skb); +int ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 2683df91807..092a017b237 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -369,60 +369,12 @@ static void ieee80211_tasklet_handler(unsigned long data) } } -/* Remove added headers (e.g., QoS control), encryption header/MIC, etc. to - * make a prepared TX frame (one that has been given to hw) to look like brand - * new IEEE 802.11 frame that is ready to go through TX processing again. - */ -static void ieee80211_remove_tx_extra(struct ieee80211_local *local, - struct ieee80211_key *key, - struct sk_buff *skb) -{ - unsigned int hdrlen, iv_len, mic_len; - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - - hdrlen = ieee80211_hdrlen(hdr->frame_control); - - if (!key) - goto no_key; - - switch (key->conf.alg) { - case ALG_WEP: - iv_len = WEP_IV_LEN; - mic_len = WEP_ICV_LEN; - break; - case ALG_TKIP: - iv_len = TKIP_IV_LEN; - mic_len = TKIP_ICV_LEN; - break; - case ALG_CCMP: - iv_len = CCMP_HDR_LEN; - mic_len = CCMP_MIC_LEN; - break; - default: - goto no_key; - } - - if (skb->len >= hdrlen + mic_len && - !(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) - skb_trim(skb, skb->len - mic_len); - if (skb->len >= hdrlen + iv_len) { - memmove(skb->data + iv_len, skb->data, hdrlen); - hdr = (struct ieee80211_hdr *)skb_pull(skb, iv_len); - } - -no_key: - if (ieee80211_is_data_qos(hdr->frame_control)) { - hdr->frame_control &= ~cpu_to_le16(IEEE80211_STYPE_QOS_DATA); - memmove(skb->data + IEEE80211_QOS_CTL_LEN, skb->data, - hdrlen - IEEE80211_QOS_CTL_LEN); - skb_pull(skb, IEEE80211_QOS_CTL_LEN); - } -} - static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, struct sta_info *sta, struct sk_buff *skb) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + sta->tx_filtered_count++; /* @@ -464,16 +416,15 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, */ if (test_sta_flags(sta, WLAN_STA_PS) && skb_queue_len(&sta->tx_filtered) < STA_MAX_TX_BUFFER) { - ieee80211_remove_tx_extra(local, sta->key, skb); skb_queue_tail(&sta->tx_filtered, skb); return; } - if (!test_sta_flags(sta, WLAN_STA_PS) && !skb->requeue) { + if (!test_sta_flags(sta, WLAN_STA_PS) && + !(info->flags & IEEE80211_TX_INTFL_RETRIED)) { /* Software retry the packet once */ - skb->requeue = 1; - ieee80211_remove_tx_extra(local, sta->key, skb); - dev_queue_xmit(skb); + info->flags |= IEEE80211_TX_INTFL_RETRIED; + ieee80211_add_pending_skb(local, skb); return; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 75412518510..de5bba7f910 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -797,8 +797,7 @@ static int ap_sta_ps_end(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - struct sk_buff *skb; - int sent = 0; + int sent, buffered; atomic_dec(&sdata->bss->num_sta_ps); @@ -814,22 +813,16 @@ static int ap_sta_ps_end(struct sta_info *sta) #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ /* Send all buffered frames to the station */ - while ((skb = skb_dequeue(&sta->tx_filtered)) != NULL) { - sent++; - skb->requeue = 1; - dev_queue_xmit(skb); - } - while ((skb = skb_dequeue(&sta->ps_tx_buf)) != NULL) { - local->total_ps_buffered--; - sent++; + sent = ieee80211_add_pending_skbs(local, &sta->tx_filtered); + buffered = ieee80211_add_pending_skbs(local, &sta->ps_tx_buf); + sent += buffered; + local->total_ps_buffered -= buffered; + #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "%s: STA %pM aid %d send PS frame " - "since STA not sleeping anymore\n", sdata->dev->name, - sta->sta.addr, sta->sta.aid); + printk(KERN_DEBUG "%s: STA %pM aid %d sending %d filtered/%d PS frames " + "since STA not sleeping anymore\n", sdata->dev->name, + sta->sta.addr, sta->sta.aid, sent - buffered, buffered); #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ - skb->requeue = 1; - dev_queue_xmit(skb); - } return sent; } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1436f747531..bfaa9ce3314 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -400,6 +400,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) sta_info_set_tim_bit(sta); info->control.jiffies = jiffies; + info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; skb_queue_tail(&sta->ps_tx_buf, tx->skb); return TX_QUEUED; } @@ -420,7 +421,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) * frame filtering and keeps a station blacklist on its own * (e.g: p54), so that frames can be delivered unimpeded. * - * Note: It should be save to disable the filter now. + * Note: It should be safe to disable the filter now. * As, it is really unlikely that we still have any pending * frame for this station in the hw's buffers/fifos left, * that is not rejected with a unsuccessful tx_status yet. diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 22f63815fb3..66ce96a69f3 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -341,6 +341,52 @@ void ieee80211_stop_queue(struct ieee80211_hw *hw, int queue) } EXPORT_SYMBOL(ieee80211_stop_queue); +void ieee80211_add_pending_skb(struct ieee80211_local *local, + struct sk_buff *skb) +{ + struct ieee80211_hw *hw = &local->hw; + unsigned long flags; + int queue = skb_get_queue_mapping(skb); + + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + __ieee80211_stop_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + __ieee80211_stop_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_PENDING); + skb_queue_tail(&local->pending[queue], skb); + __ieee80211_wake_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); +} + +int ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs) +{ + struct ieee80211_hw *hw = &local->hw; + struct sk_buff *skb; + unsigned long flags; + int queue, ret = 0, i; + + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + for (i = 0; i < hw->queues; i++) + __ieee80211_stop_queue(hw, i, + IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + + while ((skb = skb_dequeue(skbs))) { + ret++; + queue = skb_get_queue_mapping(skb); + skb_queue_tail(&local->pending[queue], skb); + } + + for (i = 0; i < hw->queues; i++) { + if (ret) + __ieee80211_stop_queue(hw, i, + IEEE80211_QUEUE_STOP_REASON_PENDING); + __ieee80211_wake_queue(hw, i, + IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + } + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + return ret; +} + void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, enum queue_stop_reason reason) { diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 694343b9102..116a923b14d 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -101,7 +101,7 @@ u16 ieee80211_select_queue(struct net_device *dev, struct sk_buff *skb) * Now we know the 1d priority, fill in the QoS header if * there is one (and we haven't done this before). */ - if (!skb->requeue && ieee80211_is_data_qos(hdr->frame_control)) { + if (ieee80211_is_data_qos(hdr->frame_control)) { u8 *p = ieee80211_get_qos_ctl(hdr); u8 ack_policy = 0; tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; -- cgit v1.2.3-70-g09d2 From fe55f6d5c0cfec4a710ef6ff63f162b99d5f7842 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Sat, 30 Aug 2008 12:16:35 +0200 Subject: net: use kmemcheck bitfields API for skbuff Signed-off-by: Vegard Nossum --- include/linux/skbuff.h | 7 +++++++ net/core/skbuff.c | 8 ++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5fd389162f0..ed6537fc5b4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -15,6 +15,7 @@ #define _LINUX_SKBUFF_H #include +#include #include #include #include @@ -346,6 +347,7 @@ struct sk_buff { }; }; __u32 priority; + kmemcheck_bitfield_begin(flags1); __u8 local_df:1, cloned:1, ip_summed:2, @@ -356,6 +358,7 @@ struct sk_buff { ipvs_property:1, peeked:1, nf_trace:1; + kmemcheck_bitfield_end(flags1); __be16 protocol; void (*destructor)(struct sk_buff *skb); @@ -375,6 +378,8 @@ struct sk_buff { __u16 tc_verd; /* traffic control verdict */ #endif #endif + + kmemcheck_bitfield_begin(flags2); #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif @@ -382,6 +387,8 @@ struct sk_buff { __u8 do_not_encrypt:1; __u8 requeue:1; #endif + kmemcheck_bitfield_end(flags2); + /* 0/13/14 bit hole */ #ifdef CONFIG_NET_DMA diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c2e4fb8f354..f0c4c6ad774 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include @@ -201,6 +202,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; + kmemcheck_annotate_bitfield(skb, flags1); + kmemcheck_annotate_bitfield(skb, flags2); /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); atomic_set(&shinfo->dataref, 1); @@ -217,6 +220,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, struct sk_buff *child = skb + 1; atomic_t *fclone_ref = (atomic_t *) (child + 1); + kmemcheck_annotate_bitfield(child, flags1); + kmemcheck_annotate_bitfield(child, flags2); skb->fclone = SKB_FCLONE_ORIG; atomic_set(fclone_ref, 1); @@ -633,6 +638,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; + + kmemcheck_annotate_bitfield(n, flags1); + kmemcheck_annotate_bitfield(n, flags2); n->fclone = SKB_FCLONE_UNAVAILABLE; } -- cgit v1.2.3-70-g09d2 From a42fc8f6943127787ad2a416436cf211d5531229 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 16 Jun 2009 16:56:38 +0000 Subject: skbuff.h: fix skb_dst kernel-doc Fix kernel-doc warnings (missing + extra entries) in skbuff.h. Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fa51293f270..3d289367aae 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -264,7 +264,7 @@ typedef unsigned char *sk_buff_data_t; * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header - * @dst: destination entry + * @_skb_dst: destination entry * @sp: the security path, used for xfrm * @cb: Control buffer. Free for use by every layer. Put private vars here * @len: Length of actual data -- cgit v1.2.3-70-g09d2